" a* Q% K, [7 [% m
├─001_machine_learning_by_andrew_ng_coursera4 _/ ?1 Q' y2 k7 S) T
│ └─001_machine_learning_by_andrew_ng_coursera
/ r0 O- C& L; F W: } │ ├─ml-003
$ c9 z9 l. Z9 ]+ B) p; ~# L │ │ ├─01_I._Introduction
+ u3 A9 q6 Q2 f8 G1 T │ │ │ 01_Welcome.mp4
8 m: b( X" c5 m, m6 L. G. b │ │ │ 01_Welcome.pdf
5 ?+ y7 Y; W: @5 J# C' s │ │ │ 01_Welcome.pptx
: `6 r V6 D8 K/ ]9 m2 f# s( @4 G& t │ │ │ 01_Welcome.srt: G( e# g! T6 `4 c% x' E% ?1 w/ d& x
│ │ │ 01_Welcome.txt6 _/ w) J) ^& u* Q
│ │ │ 02_What_is_Machine_Learning.mp4
$ ~0 t$ H" [+ x; \, @ │ │ │ 02_What_is_Machine_Learning.srt; J7 b) o- E k$ U( s* e2 O+ o6 `% C3 h
│ │ │ 02_What_is_Machine_Learning.txt
9 Q9 u* f2 K F │ │ │ 03_Supervised_Learning.mp4
* Z! h& c, S5 R │ │ │ 03_Supervised_Learning.srt
' S& L: E, l# y │ │ │ 03_Supervised_Learning.txt
+ l) J* q, y. |5 d8 i │ │ │ 04_Unsupervised_Learning.mp4: g' N; z* j7 `0 s5 |0 j
│ │ │ 04_Unsupervised_Learning.srt$ y7 J& n+ o5 U7 H
│ │ │ 04_Unsupervised_Learning.txt1 A; x( G' c' o
│ │ │
0 U" j& r* B' U+ P9 Q │ │ ├─02_II._Linear_Regression_with_One_Variable/ V0 B: {4 w2 P7 H
│ │ │ 02_Cost_Function.mp4$ g. J* }( I$ s$ H
│ │ │ 02_Cost_Function.srt1 G x! I$ ^4 r5 o8 \
│ │ │ 02_Cost_Function.txt
5 @+ _! Q" H6 o' S( U │ │ │ 05_Gradient_Descent.mp4& m) C9 L+ C- _2 N( \1 J+ m5 |* F5 ?
│ │ │ 05_Gradient_Descent.srt& C8 L4 ^" y# Z4 Y' m& c
│ │ │ 05_Gradient_Descent.txt8 p; y2 ^% I/ N% }
│ │ │ 08_Whats_Next.mp4
$ O) M( i8 {* c w6 e4 g │ │ │ 08_Whats_Next.srt
7 s$ S9 i7 M0 v# y' N1 S │ │ │ 08_Whats_Next.txt& j& m5 F% c5 D3 d6 A8 d3 m
│ │ │
" X5 e7 i1 Y9 P1 }, o │ │ ├─03_III._Linear_Algebra_Review4 F2 S; V2 @3 y, x% o6 }0 A
│ │ │ 01_Matrices_and_Vectors.mp4; e0 G @6 @/ h
│ │ │ 01_Matrices_and_Vectors.pdf2 l {; \ X" ]0 i) _$ V2 m% W" B
│ │ │ 01_Matrices_and_Vectors.pptx4 u8 J" N, T; M% _" z6 I: B- ?
│ │ │ 01_Matrices_and_Vectors.srt( ~: T$ G$ Q* p# U5 c
│ │ │ 01_Matrices_and_Vectors.txt8 }% Q( b, w0 k* p. L# G* @
│ │ │ 03_Matrix_Vector_Multiplication.mp43 }% }7 f C# a. G8 J- c
│ │ │ 03_Matrix_Vector_Multiplication.srt. t* g: t: ~9 X2 q \# J: H+ |
│ │ │ 03_Matrix_Vector_Multiplication.txt
8 y, B0 [1 O& B0 j( j/ r0 G7 ~ │ │ │ 04_Matrix_Matrix_Multiplication.mp4
7 c, l+ I: _* s │ │ │ 04_Matrix_Matrix_Multiplication.srt
- a& x- G( n7 M) m+ P1 C │ │ │ 04_Matrix_Matrix_Multiplication.txt2 C9 U3 Q& _+ D
│ │ │ 05_Matrix_Multiplication_Properties.mp4% ?6 h" |, w% R3 M* K I
│ │ │ 05_Matrix_Multiplication_Properties.srt
7 t: v5 v( u& ] │ │ │ 05_Matrix_Multiplication_Properties.txt
5 R/ i% l" N, u8 \: T, F2 D9 s │ │ │ 06_Inverse_and_Transpose.mp4* l0 p6 K3 I# ^' ~
│ │ │ 06_Inverse_and_Transpose.srt1 G- A+ y S" v" P$ H
│ │ │ 06_Inverse_and_Transpose.txt
3 ~" g3 B7 b5 e2 B │ │ │
! G7 g7 {% ^* U1 P2 J4 D, S6 L* u │ │ ├─04_IV._Linear_Regression_with_Multiple_Variables
. d9 t: P/ A( c! b# I │ │ ├─05_V._Octave_Tutorial
/ W; ]- [ @) H. L- C3 n# J b) e- E │ │ │ 01_Basic_Operations.mp4; e) f- v% O6 X# H/ _
│ │ │ 01_Basic_Operations.pdf6 y% W0 C- q% ^, q O3 b
│ │ │ 01_Basic_Operations.pptx& U- a( v& E# \1 O7 Z* ?
│ │ │ 01_Basic_Operations.srt
* X' h1 M( p1 y │ │ │ 01_Basic_Operations.txt3 ~0 b7 k7 q. ~: I
│ │ │ 02_Moving_Data_Around.mp4
) m; ^6 a) |0 Y4 R* H │ │ │ 02_Moving_Data_Around.srt
- S3 r5 G8 K6 T' u9 h. ] │ │ │ 02_Moving_Data_Around.txt
/ V' H$ \* J; z │ │ │ 03_Computing_on_Data.mp4
7 _: M( e0 {$ p0 x1 G2 \9 } │ │ │ 03_Computing_on_Data.srt
* h" ?) S. n. k! z │ │ │ 03_Computing_on_Data.txt
$ v$ P* _: E) v! E" _9 x/ q │ │ │ 04_Plotting_Data.mp4
. r% \$ I1 q X3 i4 ? │ │ │ 04_Plotting_Data.srt, N+ \2 t8 T2 m k
│ │ │ 04_Plotting_Data.txt9 b4 r" g; m$ H% a- c, g
│ │ │ 06_Vectorization.mp4 p* Z' z( }% u4 H- b' o9 `+ _% d8 e& \
│ │ │ 06_Vectorization.srt# N a! V/ U! ]) o4 p
│ │ │ 06_Vectorization.txt
4 ]& G# G( |8 C. T, @ │ │ │
, f$ _% @! o6 O9 C: k │ │ ├─06_VI._Logistic_Regression0 [8 b3 y/ r J. f! T3 x
│ │ │ 01_Classification.mp4, ^. ^( I& j* Z& I" Z) Y7 O! o
│ │ │ 01_Classification.pdf; U6 P/ U d. f( m" u
│ │ │ 01_Classification.pptx
|8 o# y' M5 j% u% K( H │ │ │ 01_Classification.srt) b; u9 N$ B: f
│ │ │ 01_Classification.txt
) R; J$ a% x5 O ]2 E │ │ │ 02_Hypothesis_Representation.mp4
* o+ `6 S7 w& J0 F/ D5 d │ │ │ 02_Hypothesis_Representation.srt
4 j2 Y% ^- r/ h* x9 L/ R: I: O │ │ │ 02_Hypothesis_Representation.txt
: I6 y X$ ]3 i; `5 Z6 Y. o' h │ │ │ 03_Decision_Boundary.mp41 Z% e) c% K+ h- }) a
│ │ │ 03_Decision_Boundary.srt
+ n. M; i7 T5 ~, W │ │ │ 03_Decision_Boundary.txt- T- U9 Y- |* w& Z6 H, w/ D
│ │ │ 04_Cost_Function.mp4! `4 k) e! t+ n6 b0 @( v$ v# N O
│ │ │ 04_Cost_Function.srt. _2 T. n' M( I( }# z
│ │ │ 04_Cost_Function.txt
1 }% A2 c# E' A. p: B │ │ │ 06_Advanced_Optimization.mp4
! r+ r8 W5 r' E; n9 s │ │ │ 06_Advanced_Optimization.srt
0 p9 U7 A, O0 I7 { │ │ │ 06_Advanced_Optimization.txt
" A- I- R/ c2 F: R+ O │ │ │
* u/ r7 s& J" d# ~ │ │ ├─07_VII._Regularization
6 B: z9 u' P$ z# d$ G) @ │ │ │ 01_The_Problem_of_Overfitting.mp4
# g$ c! F: q/ q& j" n: M │ │ │ 01_The_Problem_of_Overfitting.pdf/ {, H' @: u1 u0 b5 |. {; l! f
│ │ │ 01_The_Problem_of_Overfitting.pptx5 j* ~3 }, \; e7 v
│ │ │ 01_The_Problem_of_Overfitting.srt! S. b7 O$ r# C9 ]( L3 _' j, L" l2 o
│ │ │ 01_The_Problem_of_Overfitting.txt; f3 ?: F2 H( b: s5 ~: [
│ │ │ 02_Cost_Function.mp4/ S3 |, m% w4 L+ c+ `( J5 p
│ │ │ 02_Cost_Function.srt6 v6 v" y. l3 z9 T; ?
│ │ │ 02_Cost_Function.txt3 K4 a0 ?. @( o+ [+ }
│ │ │ 03_Regularized_Linear_Regression.mp4( |9 Y# \) W7 i( w- r" p
│ │ │ 03_Regularized_Linear_Regression.srt! g1 v# j0 ` g& [6 b5 {
│ │ │ 03_Regularized_Linear_Regression.txt
# g, D. l f& H9 `' l │ │ │ 04_Regularized_Logistic_Regression.mp4
. q! ~8 X( r; {$ f* w% P │ │ │ 04_Regularized_Logistic_Regression.srt
/ P" k# ~* x* }# z │ │ │ 04_Regularized_Logistic_Regression.txt. T# L0 r- r& z' A1 `2 P, q2 j
│ │ │
3 q$ M% {$ p5 m8 o# Y8 U: R │ │ ├─08_VIII._Neural_Networks-_Representation
3 @/ ~* W1 k, e- {1 `9 \ │ │ │ 01_Non-linear_Hypotheses.mp4
, h2 ?. j- [1 n0 ] │ │ │ 01_Non-linear_Hypotheses.pdf
9 T8 ^- |) c/ y/ G8 u │ │ │ 01_Non-linear_Hypotheses.srt
: d: G- J) G% A( M │ │ │ 01_Non-linear_Hypotheses.txt) B, E* L J: Z4 V
│ │ │ 02_Neurons_and_the_Brain.mp4
) ?3 r6 T7 w+ c$ k, b- b │ │ │ 02_Neurons_and_the_Brain.srt
5 l% l8 ?- ~, {/ I2 O3 P1 H │ │ │ 02_Neurons_and_the_Brain.txt
0 l: ~9 ~" M. t │ │ │ 3 D" A% F& K V: l5 h
│ │ ├─09_IX._Neural_Networks-_Learning
1 f2 o( f Y$ L$ e4 O │ │ │ 01_Cost_Function.mp4
" _( X2 I: e5 b │ │ │ 01_Cost_Function.pdf
B/ R+ d( b5 r │ │ │ 01_Cost_Function.pptx
4 ]; D) f! ? J │ │ │ 01_Cost_Function.srt7 ? L3 d6 Q% K
│ │ │ 01_Cost_Function.txt- {3 d4 u& Q2 f
│ │ │ 02_Backpropagation_Algorithm.mp4
% ~7 O$ [/ E* X: u0 L$ t5 s │ │ │ 02_Backpropagation_Algorithm.srt
( t& g' A4 K1 a │ │ │ 02_Backpropagation_Algorithm.txt
: h, V' ^4 k( p' Q# V" q, W% D │ │ │ 03_Backpropagation_Intuition.mp4
I! G' @% t& Y │ │ │ 03_Backpropagation_Intuition.srt- [9 I% h0 h7 e+ A
│ │ │ 03_Backpropagation_Intuition.txt6 n5 L$ [2 R. s5 |7 i
│ │ │ 05_Gradient_Checking.mp4
% N4 s5 x# X8 V1 R; Y │ │ │ 05_Gradient_Checking.srt
7 e* K: q; \$ _! x# Y7 K │ │ │ 05_Gradient_Checking.txt
, r2 c6 R. m- B1 v │ │ │ 06_Random_Initialization.mp49 C4 O" |6 f. _4 X2 Z# v
│ │ │ 06_Random_Initialization.srt
9 `4 e2 E) p5 \ │ │ │ 06_Random_Initialization.txt
- F( a4 B* M/ Z6 i Y │ │ │ 07_Putting_It_Together.mp4. j1 \) \& @7 T9 n( K1 o8 ^. n
│ │ │ 07_Putting_It_Together.srt6 I7 y2 b7 A# \& i* a( P) ]
│ │ │ 07_Putting_It_Together.txt1 K) D# @7 R, a1 T( Y& y2 }
│ │ │ 08_Autonomous_Driving.mp4
2 w A0 m. K/ T" Y3 I* M │ │ │ 08_Autonomous_Driving.srt: J; {& Z! ]3 O# D" m p7 D
│ │ │ 08_Autonomous_Driving.txt8 c0 L# P& G8 Q5 [( g
│ │ │
8 S, N# w$ d2 Y( Q9 c3 }# t │ │ ├─10_X._Advice_for_Applying_Machine_Learning
3 P1 L7 r" i+ c) a( E │ │ │ 06_Learning_Curves.mp4
% \* E' L5 O6 x" `. U, U4 Y9 z9 n │ │ │ 06_Learning_Curves.srt+ ~3 }2 Y2 T1 v( f
│ │ │ 06_Learning_Curves.txt. B. x }: ^# e. B$ C8 w% j
│ │ │ 0 u3 l& P# C1 D y
│ │ ├─11_XI._Machine_Learning_System_Design* O; t& O+ \1 a
│ │ │ 02_Error_Analysis.mp43 d! F% ^0 a& f, ?- L6 ~1 x$ ~
│ │ │ 02_Error_Analysis.srt: b6 D9 C/ m6 D
│ │ │ 02_Error_Analysis.txt: ]* Z9 A/ s* j; n4 T2 z
│ │ │
! z0 c F. O0 L! @6 H) D1 r; a │ │ ├─12_XII._Support_Vector_Machines
( i& Z/ B, e& |5 f0 p │ │ │ 01_Optimization_Objective.mp4
( p) \# n5 H, J# o/ \ │ │ │ 01_Optimization_Objective.pdf( B: n# Q( n$ y: z
│ │ │ 01_Optimization_Objective.pptx0 Z" b3 P% a0 w
│ │ │ 01_Optimization_Objective.srt
, \; a3 G8 B a4 y' Y! M │ │ │ 01_Optimization_Objective.txt
. T, k" R4 m8 }8 I5 q │ │ │ 02_Large_Margin_Intuition.mp4
1 `- F. N& o _ │ │ │ 02_Large_Margin_Intuition.srt" d' r! Y! g9 Z3 b
│ │ │ 02_Large_Margin_Intuition.txt5 ^- V5 z6 m$ }- D' |" d4 \
│ │ │ 04_Kernels_I.mp4 K9 k& Q- S! H. f' \
│ │ │ 04_Kernels_I.srt
/ r( U, T) {$ ^4 U L- o │ │ │ 04_Kernels_I.txt
3 q B! ?) X3 q* [2 e$ ^ │ │ │ 05_Kernels_II.mp4
! d$ b7 n* M7 E- o1 w% u. p( I │ │ │ 05_Kernels_II.srt# M) ~: z8 U& k9 T/ M8 O
│ │ │ 05_Kernels_II.txt
$ s5 Q5 {" x) D1 F* V- _+ | │ │ │ 06_Using_An_SVM.mp4: j' ~) w; b6 X* _7 s
│ │ │ 06_Using_An_SVM.srt
" U' K" N$ p- e5 Y/ p │ │ │ 06_Using_An_SVM.txt
/ g" G D1 k2 O- F# d- Q. E │ │ │ ( Y {! v0 A9 T( ^9 _
│ │ ├─13_XIII._Clustering. g" `% X; N0 a
│ │ │ 01_Unsupervised_Learning-_Introduction.mp4
; Z4 q( K. E7 c; e/ E │ │ │ 01_Unsupervised_Learning-_Introduction.pdf# V: y. c1 \; D5 F0 Q% F+ Y
│ │ │ 01_Unsupervised_Learning-_Introduction.pptx# ~2 C2 F/ I/ c' ]: a
│ │ │ 01_Unsupervised_Learning-_Introduction.srt) b/ l' }& G" \4 O
│ │ │ 01_Unsupervised_Learning-_Introduction.txt) j8 P& n; }% y& \+ h( m5 r6 j V: B" X
│ │ │ 02_K-Means_Algorithm.mp4
0 p9 \9 \. e) h8 }8 i' O! p6 } │ │ │ 02_K-Means_Algorithm.srt0 ^( X6 x! t) E- ~6 b
│ │ │ 02_K-Means_Algorithm.txt* Z: d- L3 Z; [) d3 ^7 W
│ │ │ 03_Optimization_Objective.mp4
% R T3 ]. X& p' J# h8 l | │ │ │ 03_Optimization_Objective.srt
7 x' D+ m/ s* o+ q [2 s) T │ │ │ 03_Optimization_Objective.txt# I7 k: \- ^, J' F; \. P
│ │ │ 04_Random_Initialization.mp4
8 A9 c3 y# ?. R- B8 O. S │ │ │ 04_Random_Initialization.srt: F" H7 p3 S6 P
│ │ │ 04_Random_Initialization.txt; @. p6 E8 s1 V0 N" n9 w5 E
│ │ │ 05_Choosing_the_Number_of_Clusters.mp4
- Q& P @2 X6 P. L │ │ │ 05_Choosing_the_Number_of_Clusters.srt
* G+ K6 H5 N7 Q0 d$ u* I │ │ │ 05_Choosing_the_Number_of_Clusters.txt. N% K: `6 r! e3 [
│ │ │
- h6 G% E" U; w0 l) { │ │ ├─14_XIV._Dimensionality_Reduction
4 ~& b! t+ n& K' S7 u3 o8 E │ │ │ 02_Motivation_II-_Visualization.mp4
8 L# X) J; D6 [- F1 \; L' `/ H │ │ │ 02_Motivation_II-_Visualization.srt. E( \( m1 C- B7 V
│ │ │ 02_Motivation_II-_Visualization.txt
+ Q: U) n0 X0 R9 X; z │ │ │ 07_Advice_for_Applying_PCA.mp49 N, |+ O! c( K: a4 G+ o2 l
│ │ │ 07_Advice_for_Applying_PCA.srt
. b; n8 C& f( P5 b1 r │ │ │ 07_Advice_for_Applying_PCA.txt6 a& b4 `5 a" R/ o& b; d
│ │ │
; F4 Q$ ?: v; G W% R │ │ ├─15_XV._Anomaly_Detection$ l2 d6 e7 Y% `0 [3 t3 K
│ │ │ 01_Problem_Motivation.mp4/ u3 C2 h9 a" }7 g3 r
│ │ │ 01_Problem_Motivation.pdf
) m. r0 z$ k2 Y' L- o │ │ │ 01_Problem_Motivation.pptx
) h9 }5 [; V4 O$ q% w, G6 d5 u │ │ │ 01_Problem_Motivation.srt5 |8 f# }- I2 G! w6 D& K+ h3 [( }* a/ {
│ │ │ 01_Problem_Motivation.txt
+ K/ d! F& ~" m* `, V │ │ │ 02_Gaussian_Distribution.mp4: J# E8 o/ W5 c0 r6 K/ q, u
│ │ │ 02_Gaussian_Distribution.srt
6 s, I1 w. D0 K1 z8 h5 J. U! a │ │ │ 02_Gaussian_Distribution.txt- q* t& w: H( S) i0 |# i) r
│ │ │ 03_Algorithm.mp4
% A5 u+ a( o! m! Z7 b │ │ │ 03_Algorithm.srt
) G3 Q8 }8 ?! s# S2 l │ │ │ 03_Algorithm.txt
' l" Z. a8 }; D: ?' z- b6 F │ │ │ 06_Choosing_What_Features_to_Use.mp47 d! O; J1 X* ]+ J* q4 D8 l4 r
│ │ │ 06_Choosing_What_Features_to_Use.srt
2 O& I% R* u7 O6 p$ X( W! h/ y5 K │ │ │ 06_Choosing_What_Features_to_Use.txt
& F- Y8 q5 c# S& t4 M3 c │ │ │ 9 B8 L: c/ _: ]- L+ E1 a
│ │ ├─16_XVI._Recommender_Systems
5 W) s2 m' T7 q$ ?$ W │ │ │ 01_Problem_Formulation.mp44 _+ h* i$ Z; ]& k; y1 K
│ │ │ 01_Problem_Formulation.pdf
8 q2 a9 o G! K │ │ │ 01_Problem_Formulation.pptx
; g$ S: s+ Y/ S9 a- y3 I │ │ │ 01_Problem_Formulation.srt
8 t1 K8 h5 n# \: \/ Y │ │ │ 01_Problem_Formulation.txt) I( z3 e0 d- `5 [, n5 X0 c4 y
│ │ │ 02_Content_Based_Recommendations.mp44 h2 ^1 D4 ?& K
│ │ │ 02_Content_Based_Recommendations.srt$ z* D& A/ t4 E. A# j
│ │ │ 02_Content_Based_Recommendations.txt9 Y# R7 L- g6 D5 W4 n0 f, o
│ │ │ 03_Collaborative_Filtering.mp42 U( U0 D+ L; T: k
│ │ │ 03_Collaborative_Filtering.srt( P Y/ H$ l' {& F; _
│ │ │ 03_Collaborative_Filtering.txt
) y+ @- q! h5 \+ Q4 n+ Q │ │ │ 04_Collaborative_Filtering_Algorithm.mp4
* `. R, h6 I) m& q, V │ │ │ 04_Collaborative_Filtering_Algorithm.srt( e3 R& T6 z9 X, G* g( H
│ │ │ 04_Collaborative_Filtering_Algorithm.txt
& P# q2 H5 }1 ] │ │ │
+ E/ s6 f* Z& m0 O │ │ ├─17_XVII._Large_Scale_Machine_Learning
% A$ ~5 q. U0 R9 X" R │ │ │ 05_Online_Learning.mp4
6 V2 d- }0 c. q) P k6 z' o │ │ │ 05_Online_Learning.srt
9 [% ]6 I( p6 X5 s1 D │ │ │ 05_Online_Learning.txt
7 {8 B/ [" M: L/ D6 P0 ?: |0 n- j1 R │ │ │ : Z4 _7 j# @8 G; W. Z
│ │ ├─18_XVIII._Application_Example-_Photo_OCR6 E m7 s- p( R" G |- ~2 N- E
│ │ │ 02_Sliding_Windows.mp4) E* N0 o1 E! n4 P- ^
│ │ │ 02_Sliding_Windows.srt$ F7 W1 q( r2 d
│ │ │ 02_Sliding_Windows.txt2 C. B$ u7 y% k5 l" W! F/ h& Z6 E7 n' d
│ │ │
4 h- n0 @7 t5 b! I R8 N │ │ └─19_XIX._Conclusion
( H: h) p2 f+ C* ]! e │ │ 01_Summary_and_Thank_You.mp4
0 [% F0 k; }: Q5 Y b" L+ k+ d │ │ 01_Summary_and_Thank_You.srt
2 {5 t) S4 D5 Q- e1 B" ~6 Q2 X7 p │ │ 01_Summary_and_Thank_You.txt
3 a( g+ S" F, P │ │
9 t) O' `' h1 D8 j │ └─机器学习-斯坦福-Andrew NG-2012
- ]: z, ?1 S4 g0 Y( _' ] M( Y0 t │ │ 下载说明.txt$ S4 e( X M8 A+ B1 s- i
│ │ 关注我们.png
" i/ w$ w$ B# {0 c z. b │ │ 攻城狮论坛=网络技术+编程视频.url+ e" A3 p9 D" {' _
│ │ 机器学习笔记2012_v0.1.pdf6 }3 g8 b- D1 B- ]) F9 V
│ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt4 u1 L( D* n, J" n
│ │ 6 i2 n! ?3 y N( \/ R+ i( n( c
│ ├─week 1
: d' D! W2 n- W7 v. E( J, | │ │ 1 - 1 - Welcome (7 min).mp4# L0 [6 w' r' C! N! f1 u3 ?% j
│ │ 1 - 1 - Welcome (7 min).srt5 I0 ^' I7 X! m/ [8 q- F
│ │ 1 - 2 - What is Machine Learning (7 min).mp4. F4 k) g1 d2 q
│ │ 1 - 2 - What is Machine Learning- (7 min).srt
) f. ~4 `& R: c5 Z+ \5 L; D- n │ │ 1 - 3 - Supervised Learning (12 min).mp4
1 ]4 J! ]* |9 G% D2 v- z │ │ 1 - 3 - Supervised Learning (12 min).srt
6 R: l# P" P! Q! J │ │ 1 - 4 - Unsupervised Learning (14 min).mp48 c* b8 v7 s8 ]& ]6 R! @6 G6 }
│ │ 1 - 4 - Unsupervised Learning (14 min).srt; d, H( _* E% d# i3 U
│ │ 2 - 1 - Model Representation (8 min).mp4
" H: A/ c7 ^% e, ?+ M- k │ │ 2 - 1 - Model Representation (8 min).srt' M9 M8 A; ]9 {4 x( b. w
│ │ 2 - 2 - Cost Function (8 min).mp4
" Q% R1 d7 k7 C2 J: S m2 j │ │ 2 - 2 - Cost Function (8 min).srt
9 _& X/ c! e+ V/ w* r& n# R/ h! c │ │ 2 - 5 - Gradient Descent (11 min).mp4
2 i) G# A& S' _( d& p( r │ │ 2 - 5 - Gradient Descent (11 min).srt
* o6 r6 P& K# X, `3 r │ │ 2 - 8 - What's Next (6 min).srt
5 N6 m q, H, X! Y( @% ` │ │ 2 - 8 - Whats Next (6 min).mp4
8 M( A8 `/ T- s8 k │ │ 3 - 1 - Matrices and Vectors (9 min).mp4
% v. J# `- S; }7 j2 V │ │ 3 - 1 - Matrices and Vectors (9 min).srt
! A: [8 _; U% s( |* |3 q d │ │ $ K2 w) @" x% ~6 n/ z
│ ├─week 10
" I4 a" ?, k3 A' s# L, [ │ │ 17 - 5 - Online Learning (13 min).mp46 I: H" c* g& b+ M, m6 x# H" V, j
│ │ 17 - 5 - Online Learning (13 min).srt
2 s: z9 F* A% I) C0 h │ │ Lecture17.pdf2 a7 W9 A5 J$ S3 x
│ │ 6 T0 n7 `, X/ G7 p
│ ├─week 2
* ?9 `2 K, b2 g- D │ │ 4 - 1 - Multiple Features (8 min).mp4
. V2 S* e6 ?+ s │ │ 4 - 1 - Multiple Features (8 min).srt
7 V- P0 X& x1 r │ │ 4 - 6 - Normal Equation (16 min).mp4
& R, c. m/ c. R2 j │ │ 4 - 6 - Normal Equation (16 min).srt8 s6 E0 n2 f/ b) p
│ │ 5 - 1 - Basic Operations (14 min).mp4
1 {3 T: j' ~* t# \/ x │ │ 5 - 1 - Basic Operations (14 min).srt4 Z- O; X. |# x; d1 ]
│ │ 5 - 2 - Moving Data Around (16 min).mp4' J+ g. b; l" a' `! V2 W
│ │ 5 - 2 - Moving Data Around (16 min).srt
; _0 v; x; c$ T, o7 ] │ │ 5 - 3 - Computing on Data (13 min).mp47 S+ Y# L _9 m
│ │ 5 - 3 - Computing on Data (13 min).srt
: C( X, y0 s& W. M: d) ^* x │ │ 5 - 4 - Plotting Data (10 min).mp4
: i) t) M3 S/ p& p │ │ 5 - 4 - Plotting Data (10 min).srt8 u9 M# w2 P6 s+ y1 x
│ │ 5 - 6 - Vectorization (14 min).mp4
: H8 ]) \" g, @ F* d5 B% ? │ │ 5 - 6 - Vectorization (14 min).srt
8 Z2 H% H% t- X, ` │ │ Lecture4.pdf8 \0 W, |7 l/ R( K2 `) K
│ │ Lecture5_octave tutorial.pdf
3 D1 x9 ~. G* u7 M' X8 e) Q │ │
! [3 [3 V$ {$ i │ ├─week 3
7 s5 t6 }3 l( l5 q& \' _& G │ │ 6 - 1 - Classification (8 min).mp4- r. T; S5 v2 J" R4 a; p9 N% I
│ │ 6 - 1 - Classification (8 min).srt
$ c s! K4 z' ^9 [" H; H │ │ 6 - 2 - Hypothesis Representation (7 min).mp4. _: o& U" X% b5 S
│ │ 6 - 2 - Hypothesis Representation (7 min).srt
7 ]9 v* F. _2 t1 K2 L8 z8 D │ │ 6 - 3 - Decision Boundary (15 min).mp4
* R9 d0 a6 P, P6 B _* s │ │ 6 - 3 - Decision Boundary (15 min).srt
: }( @1 D4 p# `, F) V W │ │ 6 - 4 - Cost Function (11 min).mp48 ]! R$ N$ o& b9 C. P/ h4 O
│ │ 6 - 4 - Cost Function (11 min).srt
5 H. _0 G& R! y7 S; ]7 e. H │ │ 6 - 6 - Advanced Optimization (14 min).mp4
4 e! M+ v' _% s6 `; J8 A' x │ │ 6 - 6 - Advanced Optimization (14 min).srt
0 m5 F: c3 }$ N" ]5 V │ │ 7 - 2 - Cost Function (10 min).mp4% d l# i4 X9 d! O
│ │ 7 - 2 - Cost Function (10 min).srt& g* H% y/ `7 R, ]. x# {
│ │ docs_slides_Lecture6.pdf
6 C# W* d1 P, |! m │ │ docs_slides_Lecture7.pdf% {% d$ Z( n- V. |
│ │ - {, e P( j/ t. }9 d7 K8 y7 l! F4 h
│ ├─week 46 {! I0 ?3 o, i/ C8 X
│ │ 8 - 1 - Non-linear Hypotheses (10 min).mp4
, a* k+ Q! p3 N" a+ P( g# h# _ │ │ 8 - 1 - Non-linear Hypotheses (10 min).srt
% \! \* J9 y1 k7 _$ [% _8 _) U │ │ 8 - 2 - Neurons and the Brain (8 min).mp4
5 C \2 H* g! ?6 W. b │ │ 8 - 2 - Neurons and the Brain (8 min).srt
' P E* E" w2 K1 F0 }. v0 |. v │ │ 8 - 3 - Model Representation I (12 min).mp4
: _+ R! |& P, O │ │ 8 - 3 - Model Representation I (12 min).srt
% }; S* W6 b4 M2 h3 V │ │ 8 - 4 - Model Representation II (12 min).mp43 V: h( {0 Z7 C- |& k
│ │ 8 - 4 - Model Representation II (12 min).srt g' K% \" b/ U2 M% E) V+ j: v
│ │ 8 - 5 - Examples and Intuitions I (7 min).mp4
* ~1 Q, H9 o1 v6 } │ │ 8 - 5 - Examples and Intuitions I (7 min).srt6 |4 @9 N+ h% q+ ]6 S; D& w0 @
│ │ 8 - 7 - Multiclass Classification (4 min).mp4
; z) s" P6 _9 I7 A │ │ 8 - 7 - Multiclass Classification (4 min).srt
, `& Y E, J, ?7 A' K2 n! A% _ │ │ docs_slides_Lecture8.pdf
6 |" k8 F$ j. r. S4 B6 C │ │
) U2 V9 m6 t3 h │ ├─week 56 P" @( U; y8 P
│ │ 9 - 1 - Cost Function (7 min).mp4
6 o+ S1 }7 Z! M3 X │ │ 9 - 1 - Cost Function (7 min).srt
! Y8 W) a" r% I1 D │ │ 9 - 5 - Gradient Checking (12 min).mp4* Q( d8 |" C, k& Z5 m; q
│ │ 9 - 5 - Gradient Checking (12 min).srt( l6 T" z) P4 q; N) F' Q
│ │ 9 - 6 - Random Initialization (7 min).mp4& i! R! H" Y! r+ y- _" t
│ │ 9 - 6 - Random Initialization (7 min).srt
* a, K8 m/ p- B9 ^4 w │ │ 9 - 7 - Putting It Together (14 min).mp4
" i0 f9 V. J) q1 R │ │ 9 - 7 - Putting It Together (14 min).srt
/ {$ `' V, X9 _* y) | p3 q2 T( Y │ │ 9 - 8 - Autonomous Driving (7 min).mp4
6 x9 U9 p7 {8 v6 d, Z( w │ │ 9 - 8 - Autonomous Driving (7 min).srt1 g% R+ C: @! P% O, F0 p
│ │ docs_slides_Lecture9.pdf
l& F7 c% t5 m1 J7 ]. O │ │ 0 J3 I& F3 r7 z) ?5 p! G/ R2 g! |
│ ├─week 68 k$ m" {5 B% B. y: g! N
│ │ 10 - 2 - Evaluating a Hypothesis (8 min).mp4
3 \2 v' L5 g3 O │ │ 10 - 2 - Evaluating a Hypothesis (8 min).srt3 c4 d4 W; w% n/ y5 p2 @
│ │ 10 - 6 - Learning Curves (12 min).mp4
* a6 Q2 F3 I! v5 o$ S( V" [ │ │ 10 - 6 - Learning Curves (12 min).srt
. b" B: ^0 ^( V8 ~ │ │ 11 - 2 - Error Analysis (13 min).mp4" H- q" I- @1 Q, {- s! _. E
│ │ 11 - 2 - Error Analysis (13 min).srt
' B( u2 e+ K% Q# P │ │ docs_slides_Lecture10.pdf
9 b; z, J& S7 e# g) x4 O2 o │ │
7 j9 q& @$ M0 c+ l$ b: k │ ├─week 7
! N- w# q, N- y │ │ 12 - 1 - Optimization Objective (15 min).mp4+ E% e8 G- A& S3 r
│ │ 12 - 1 - Optimization Objective (15 min).srt
% a X3 m- D* i5 r% g* n% F2 Y │ │ 12 - 2 - Large Margin Intuition (11 min).mp4
. k# u9 b: i, N, z/ b │ │ 12 - 2 - Large Margin Intuition (11 min).srt
9 i! I3 d. O9 R% m( a6 j+ x4 O │ │ 12 - 4 - Kernels I (16 min).mp4& F% }! f* C" i
│ │ 12 - 4 - Kernels I (16 min).srt
1 k3 h$ A6 A% \1 b& M! U- l │ │ 12 - 5 - Kernels II (16 min).mp4
# [+ _8 V2 {7 I/ R2 |/ K │ │ 12 - 5 - Kernels II (16 min).srt, F' i; J9 |9 D( y2 u) X; R: x
│ │ 12 - 6 - Using An SVM (21 min).mp43 u& S8 B( A+ q$ g
│ │ 12 - 6 - Using An SVM (21 min).srt
2 [( b3 q; z! A. q │ │ docs_slides_Lecture12.pdf
/ i# E, a, A$ h │ │
2 r) q& j% T/ |& K0 @ │ ├─week 8 Q* G1 G4 ]' L. X q8 h
│ │ 13 - 2 - K-Means Algorithm (13 min).mp4
5 z" ?8 R7 W ?+ B8 Q │ │ 13 - 2 - K-Means Algorithm (13 min).srt1 b& d; N" E9 B: Q1 B/ t8 n# r) ~
│ │ 13 - 3 - Optimization Objective (7 min).mp4
1 w. y% ~' a6 Z T2 y/ @1 x │ │ 13 - 3 - Optimization Objective (7 min).srt) X$ F3 {- r: M! ]/ \ k
│ │ 13 - 4 - Random Initialization (8 min).mp4
! J* B0 W: A! n" g │ │ 13 - 4 - Random Initialization (8 min).srt1 E5 Q1 \# J9 y3 f6 S3 {# F
│ │ 14 - 7 - Advice for Applying PCA (13 min).mp4
9 a. f9 h9 O( P0 r0 b │ │ 14 - 7 - Advice for Applying PCA (13 min).srt
6 a) g9 c4 @9 e% S │ │ docs_slides_Lecture13.pdf
0 U3 _* Z; V2 H' v │ │ docs_slides_Lecture14.pdf8 e7 Y! J' @6 Y0 R b
│ │
' m( `2 O' w9 G │ ├─week 9
5 w2 S+ @: a0 t R7 Q: b │ │ 15 - 1 - Problem Motivation (8 min).mp4" k' w7 b' M" ^) I
│ │ 15 - 1 - Problem Motivation (8 min).srt \4 s' `- c4 V9 q8 D$ s# f
│ │ 15 - 2 - Gaussian Distribution (10 min).mp4
/ v6 K: C; M7 M) b. \! i) y │ │ 15 - 2 - Gaussian Distribution (10 min).srt
1 q9 V# K# o- T6 A2 p │ │ 15 - 3 - Algorithm (12 min).mp4
$ T/ H* ~1 s: M1 l, K+ ?8 W/ G& } │ │ 15 - 3 - Algorithm (12 min).srt i9 S$ Z( V9 R- v, B
│ │ 16 - 1 - Problem Formulation (8 min).mp4
2 \6 g. k1 ~1 s% W& ^4 D │ │ 16 - 1 - Problem Formulation (8 min).srt4 s" H. L! r& {" |- ?1 y9 d
│ │ 16 - 3 - Collaborative Filtering (10 min).mp4
3 B2 `* |5 c* ~) v* X │ │ 16 - 3 - Collaborative Filtering (10 min).srt1 }6 R/ a/ W$ Z1 u2 y; @( n
│ │ docs_slides_Lecture15.pdf
; f2 T' B. Z# i3 g: u& @, Z │ │ docs_slides_Lecture16.pdf8 _: N% X6 u; M. e# L& u$ y
│ │
4 N: I0 n$ l5 \5 m# x │ └─作业1 @! D% n6 {8 l6 E) N
│ │ ex1.zip
6 t9 d1 o7 V, B1 y- | │ │ ex3.zip7 I( R* `( {, v) [+ h8 q& O
│ │ ex4.zip: B R. |8 n" M3 a. H+ @* J4 a e* \
│ │ ex5.zip
6 r( E: d4 k: N$ c' s# j6 V │ │ ex6.zip$ M4 V& w$ g% l7 v1 ?# |
│ │ ex7.zip! L+ H2 C# ?1 K' q g+ q8 U4 s
│ │ ex8.zip
/ i2 i0 Y" X' |' x) r │ │ Octave-3.2.4_i686-pc-mingw32_gcc-4.4.0_setup.exe& f8 U- J9 C! u6 T2 B
│ │ - N6 H1 O% d3 `+ e% \
│ └─答案/ C& m2 F6 m8 W% X: ~1 ~
│ ├─ex16 Z% q5 Y+ r J/ T7 }% l
│ │ computeCost.m
' y+ Q D! d H │ │ computeCostMulti.m
6 b# T' V1 t! m0 l* e3 B8 C, S, e │ │ ex1.m' b4 p) p- }& s* [
│ │ ex1data1.txt
" R( t5 d2 x, V2 E) U- Y1 T k ^ │ │ ex1data2.txt
; X, l; B6 i s: N: ]4 S │ │ ex1_multi.m1 P8 L0 C* K9 P0 g( ]4 O
│ │ featureNormalize.m
2 \# r6 d' \1 t( d │ │ gradientDescent.m
X4 `8 K% s/ c3 ~ │ │ gradientDescentMulti.m: x; H/ i" _5 A" U8 Z- v1 z# _( |4 A
│ │ ml_login_data.mat. {4 D6 H; t2 @3 i
│ │ normalEqn.m N I; k, z4 [, ]
│ │ plotData.m
3 h, N6 m7 t3 m7 [ │ │ submit.m' J2 B$ o ]+ L& h8 Z
│ │ submitWeb.m
0 F0 ^1 N6 {+ m" q4 H. v5 S; H$ ~ │ │ warmUpExercise.m# Y/ t) W: ?3 Y9 v3 y F& \
│ │
4 { H% I2 p# c' @$ J │ ├─ex2( o% b' Z. f" [5 @ a) ^" G9 v# Y
│ │ costFunction.m
4 m# e3 l' Y A$ m5 \! R │ │ costFunctionReg.m
' Q7 x G/ o5 `) H- J) c" y0 J │ │ ex2.m
6 a+ \0 O% n9 P7 G( K6 ? │ │ ex2data1.txt4 b, V! l2 Z) l6 E; E6 _* e9 j: c3 Y
│ │ ex2data2.txt
- O- F1 b6 g9 Z* f- |1 P │ │ ex2_reg.m
7 w9 q! s7 G, r+ T! [9 a# ? │ │ mapFeature.m/ z I6 {* j$ w) \. _- R, A( I2 h
│ │ ml_login_data.mat
* W$ m x, P+ q0 r │ │ plotData.m
4 t# z2 M4 J# Y# g │ │ plotDecisionBoundary.m
* m3 l7 E9 f/ q2 A& Q. ]/ e1 u │ │ predict(1).m.baiduyun.downloading
" M' y+ y1 X) g, s9 S │ │ predict.m; }; p$ T9 I2 i3 e4 p2 w/ \5 c" w
│ │ sigmoid.m
/ ^8 O2 H% d+ V2 F5 d9 H │ │ submit(1).m.baiduyun.downloading9 z7 ~& F0 k" \+ h1 l
│ │ submit.m
k1 A" J, F% ]7 @6 E7 B2 n) t2 H │ │ submitWeb(1).m.baiduyun.downloading7 H: K; a; [2 s4 Q0 |- K
│ │ submitWeb.m+ m2 @" k2 ?1 ~% J. v" g. h
│ │ * i( x7 m; \+ i. X
│ ├─ex3) p, \/ C% g) |2 U: H* Z- k+ c
│ │ displayData.m! i ~( x8 [$ m+ |4 E. F. x& S$ X
│ │ ex3(437).m.baiduyun.downloading* m+ S% g& D" H: m0 `
│ │ ex3.m' Z5 H* G- `: `% m
│ │ ex3data1.mat2 l7 I G: J! t1 ]5 s
│ │ ex3weights.mat) ~5 N5 q( \& x0 h
│ │ ex3_nn.m
' m! _; g7 ^7 k8 Y; V │ │ fmincg.m0 h4 [& c* |: P
│ │ lrCostFunction.m2 Q3 r! C# c1 ~1 g7 w
│ │ ml_login_data.mat$ a. I Z2 K T! f- X
│ │ oneVsAll.m" e" j/ d! o1 H! M+ q& P8 L
│ │ predict.m
9 |; O4 T9 [2 n/ v, w; S │ │ predictOneVsAll.m/ `1 u2 Z; P# [8 B) C+ S6 }8 `% W. z
│ │ sigmoid.m \# s% e+ Z: U; ]. ^/ H' ~
│ │ submit.m+ ]: F4 E. A* q }5 \
│ │ submitWeb.m1 M4 e- W, s5 b" h; m* J
│ │ 4 Q! F" w9 n$ i6 I" a- N- v
│ ├─ex4
9 Z: o5 j( X6 o. {# {1 n │ │ checkNNGradients.m
6 B- i b- r# i5 D, v: Y │ │ computeNumericalGradient.m9 e' s1 ]$ x5 }- Y" `9 i
│ │ debugInitializeWeights.m
6 `0 B! m8 }1 \2 y │ │ displayData.m- ]$ B) s+ h+ ^6 t* B
│ │ ex4.m0 W4 t1 m" c# K( J/ s1 ]
│ │ ex4data1.mat
# `2 z9 m/ i+ G0 ^7 b │ │ ex4weights.mat
' X1 Y+ m9 f5 q │ │ fmincg.m/ ?. @; |. i+ \2 z. m! t; ^
│ │ ml_login_data.mat7 f6 m3 S" q8 y J4 q$ O4 D
│ │ nnCostFunction.m i7 h1 A2 k! _- A. k
│ │ predict.m
; H8 q% H1 g* ^ z3 g │ │ randInitializeWeights.m. C1 [0 N X# l% V( y" e# }
│ │ sigmoid.m4 k- }9 ~$ ?. L9 O6 N, j, z
│ │ sigmoidGradient.m
$ U+ i4 x1 Q* j7 o% D3 C │ │ submit.m
' `: s/ [* x* f9 l+ ? │ │ submitWeb.m2 z, ] }/ s1 ~* w
│ │ . l5 ?' D% }, B" k! H& p
│ ├─ex5
9 _7 I5 W7 W: ?3 P) \( b │ │ ex5.m
' O4 v' G$ ?( m6 z5 e- u │ │ ex5data1.mat% u, f0 f% e+ ]6 i# D
│ │ featureNormalize.m
6 C: Z( G/ i3 K. B% }8 P1 M3 e │ │ fmincg.m
7 N# t$ i( `* l- i- K5 [ │ │ learningCurve.m
4 j* A% Y) ~( W │ │ linearRegCostFunction.m. i0 ]' m! |/ z/ n
│ │ ml_login_data.mat; }- v8 f- Z y1 ^, @9 y) V4 k
│ │ plotFit.m
/ Q, y: R: L: C0 G. u │ │ polyFeatures.m- D" R; a# p; s" l
│ │ submit.m* T( H! G7 \2 i! G; T n
│ │ submitWeb.m
& O7 @/ A! x; b: ^9 _8 ?3 e; a │ │ trainLinearReg.m
) S: }: Z( a* ~7 |3 p │ │ validationCurve.m
4 R! o7 K* H5 N- {/ y │ │
- {- M( s; f( Z& l M0 _ │ ├─ex6% [$ x* W3 o- D$ m( H: R
│ │ dataset3Params.m
4 ^5 u( L/ R8 m2 U, k │ │ emailFeatures.m. D$ [5 |: S' e+ z
│ │ emailSample1.txt
( v4 W5 k, F; y h5 T │ │ emailSample2.txt
1 u; M3 s( O4 S8 @; j │ │ ex6.m
# ?3 Q6 ?% W1 Q$ e, G* v& ^" T │ │ ex6data1.mat
: S" Z5 ?& j5 u; W/ ^ │ │ ex6data2.mat
9 R( L1 X- `6 G' r" Z3 w4 s: U+ | │ │ ex6data3.mat( n, I: W: b9 Y4 W5 |
│ │ ex6_spam.m* q5 ]3 J. ]$ X8 [; u
│ │ gaussianKernel.m6 x& R% F: T$ H. E$ v' x
│ │ getVocabList.m P2 H( l$ V2 C( k
│ │ linearKernel.m
7 l: J& z' P/ ]/ ^ │ │ ml_login_data.mat
* D( g# m5 W _8 w4 N, v │ │ octave-core3 W7 O9 p0 \$ d0 D
│ │ plotData.m$ V& Y9 `$ R5 W9 P* @
│ │ porterStemmer.m
2 m; x" c1 F( }0 y" D* L │ │ processEmail.m
, M: n0 q8 [% Q# a/ T% Y! g │ │ readFile.m
# D- F& P/ X! a6 ?2 g │ │ spamSample1.txt
) V7 b2 g( A1 U( e! \# L │ │ spamSample2.txt3 G) P/ [7 A# J: V6 V
│ │ spamTest.mat1 A! x, {# Q* S# k
│ │ spamTrain.mat2 Y1 A# f$ |0 l
│ │ submit.m2 o& g, a# ]% y {9 R! D# L* q. ]
│ │ submitWeb.m
) L5 \% o6 @3 @; R2 r" k( L! A │ │ svmPredict.m8 X8 L. ]) k. w& Q; O4 y
│ │ svmTrain.m; v' @( ^. R/ J! x
│ │ visualizeBoundary.m
) L# l! S2 P) ^) B6 e4 I │ │ visualizeBoundaryLinear.m3 q: Q x7 I' ]% `( `" M
│ │ vocab.txt
5 V. q* B" o+ w8 w# W │ │ . l7 A( P, c) `& O6 q$ ]
│ ├─ex76 \, Y" l/ O; n
│ │ bird_small.mat
1 m* _ M' @/ d g& S9 @ │ │ bird_small.png
9 }# Y! u# q, k" c │ │ computeCentroids.m
* z# S7 `3 ^3 e3 H │ │ displayData.m' y; \, q' g$ s q$ w8 \8 b }
│ │ drawLine.m$ P% } l0 v e) ]. Q) h* B
│ │ ex7.m
+ }1 a/ k! `! ^0 ?# d6 w! U! N# [ │ │ ex7data1.mat
" s( ^8 D. U4 `0 m7 K │ │ ex7data2.mat
8 L% d5 J. T. H4 [3 }2 c% G │ │ ex7faces.mat% d. p& Y! J; L! j: p
│ │ ex7_pca.m# H. n' ~! q, p: r
│ │ featureNormalize.m; v, Z& k+ D& n; S
│ │ findClosestCentroids.m" S3 g5 Z: a w( o
│ │ kMeansInitCentroids.m
. @$ C5 |4 `( A, N; c │ │ ml_login_data.mat
, d0 p4 z( Y9 e V0 j │ │ octave-core- n( V: G+ \2 C% K0 A) O! Z8 d3 \5 H! Y
│ │ pca.m
/ }, Y( f) I A, l! T0 u, ^3 y │ │ plotDataPoints.m, K+ h p; _( C
│ │ plotProgresskMeans.m# i- F; ]. m! y& N
│ │ projectData.m0 x( f/ l4 R0 y; u$ n8 U
│ │ recoverData.m$ b7 X `2 G* e/ [
│ │ runkMeans.m
V$ O' R% R" e5 X' s │ │ submit.m
' [) R9 z6 W4 f- B │ │ submitWeb.m+ U2 F1 f+ ] p2 {: s
│ │
& ?9 R7 j. a% I# D! M; {9 w2 Q │ └─ex8
. g, C8 ?, }9 ~ │ checkCostFunction.m: w+ n7 G4 d7 A& G, X5 P6 g/ ?
│ cofiCostFunc.m! \1 z9 `+ W' V: w7 m% [% d
│ computeNumericalGradient.m
! d1 P3 r& P# w% F │ estimateGaussian.m; z7 D- P3 ~5 |8 G$ W# \8 Q
│ ex8.m* @2 B5 n) K" S( r
│ ex8data1.mat% _9 W8 ~8 y3 q6 _4 o
│ ex8data2.mat
3 ?; `4 w" R% ?8 K% _3 t8 f: _ │ ex8_cofi.m$ |4 R/ F, R9 D1 b8 `3 V0 M6 X
│ ex8_movieParams.mat
# G# }" ]* S7 U( R8 E3 G2 }" F │ ex8_movies.mat
2 N! ^8 |* M5 t5 W" x7 Y' g, I4 a │ fmincg.m5 r1 B: |& Q) K. l' Y- v3 a
│ loadMovieList.m
$ _1 O; o8 P. i, z: f) P& r │ ml_login_data.mat
. z$ ?7 T! }& F4 I( m( e' Z, A$ c8 j │ movie_ids.txt7 H" \0 ^" A4 u5 m$ E: h+ p
│ multivariateGaussian.m8 [( O1 i W9 r5 v: Q" y/ p! _. S
│ normalizeRatings.m4 B/ y: L. H8 ~( @- F
│ selectThreshold.m, O4 n0 ] R( E6 i; Y6 P
│ submit.m
; |8 R2 \! m3 q │ submitWeb.m
1 j& t! L9 f, K% f$ l, ]+ \* n) M6 r │ visualizeFit.m
5 k# i3 H/ W4 ^8 p/ s │
& x/ {- }/ V/ A+ y: _) G* }$ G ├─003_机器学习基石, G! T; s( H4 r6 P
│ └─003_机器学习基石
2 q" ], h) a4 |" U% z: {* k2 B, k │ │ 下载说明.txt
- _/ q( g2 c7 Y. D P │ │ 关注我们.png% P( \" F) X7 \9 P% L# F; Z
│ │ 攻城狮论坛=网络技术+编程视频.url
- V# J" X' Q' e* z7 ~/ n) Z) w │ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt
4 Y, m( D4 `, F2 Y │ │ 0 ?6 _5 K/ D, f% g% s. }
│ ├─Machine Leaning Foundations - TNU
) d+ A" y5 u; B9 [, w. Y& j1 _: ~ │ │ 01_handout.pdf
% [( H5 P6 j# }" {: {+ G% b9 g. D% f │ │ 02_handout.pdf6 ^- b5 A# m5 ^/ ]" x! a! ~
│ │ 03_handout.pdf
; @* J, [# ?% q4 P/ t │ │ 04_handout.pdf
% ], x4 C0 m/ x5 J │ │ 05_handout.pdf
* U9 ~0 b' P% M" X. L5 z, n │ │ 06_handout.pdf
1 a9 r1 ~, K$ U8 F: S │ │ 07_handout.pdf
# D9 M: M* x4 P: D6 Z1 f │ │ 08_handout.pdf. d7 U0 @. D2 u0 {
│ │ 09_handout.pdf
& a' U( l; C! y! m6 }+ N │ │ 1 - 1 - Course Introduction (10-58).mp4' M5 `( b0 V, [- O7 }
│ │ 1 - 2 - What is Machine Learning (18-28).mp46 I; t+ i' O: N1 f6 Z0 w
│ │ 1 - 3 - Applications of Machine Learning (18-56).mp40 q6 |- t4 D$ m+ I% q8 q% U5 m
│ │ 1 - 4 - Components of Machine Learning (11-45).mp4
4 ~ Y; b# d% x/ Y+ P │ │ 1 - 5 - Machine Learning and Other Fields (10-21).mp4
! f/ A2 T/ v. ?0 Y+ [: c │ │ 10 - 1 - Logistic Regression Problem (14-33).mp43 k0 C; z* l6 m. v$ L( P
│ │ 10 - 2 - Logistic Regression Error (15-58).mp4" @) ]8 C7 A n7 c9 W* m: F7 I2 r" t
│ │ 10 - 3 - Gradient of Logistic Regression Error (15-38).mp4
+ k" \/ S+ J7 v$ J │ │ 10 - 4 - Gradient Descent (19-18).mp4
) W8 z3 Z2 U2 C6 t6 T9 u* g │ │ 10_handout.pdf
" K7 k9 N8 ? f5 b( Z7 d │ │ 11 - 1 - Linear Models for Binary Classification (21-35).mp49 N# g! ?' o+ Z% E& v4 B% x f* c
│ │ 11 - 2 - Stochastic Gradient Descent (11-39).mp4. h4 `5 T' b! A
│ │ 11 - 3 - Multiclass via Logistic Regression (14-18).mp4# n" t2 \5 q( W; r7 k1 p# T
│ │ 11 - 4 - Multiclass via Binary Classification (11-35).mp4
5 R4 z1 @1 ^ f' d* ` │ │ 11_handout.pdf9 Y% y2 I2 k9 p" W
│ │ 12 - 1 - Quadratic Hypothesis (23-47).mp45 _0 \ [/ ]2 b4 V# F, d
│ │ 12 - 2 - Nonlinear Transform (09-52).mp4
: R: G( @6 _. u │ │ 12 - 3 - Price of Nonlinear Transform (15-37).mp4& k" W& U, k7 r, `& k# y1 ?
│ │ 12 - 4 - Structured Hypothesis Sets (09-36).mp4
) h# z6 s+ |9 c) k/ r; j │ │ 12_handout.pdf& ~$ g3 ]& y/ e: S
│ │ 13 - 1 - What is Overfitting- (10-45).mp4 K0 [/ b4 C* |; O; t
│ │ 13 - 2 - The Role of Noise and Data Size (13-36).mp4
; t* G* \ _: K1 \% ^ │ │ 13 - 3 - Deterministic Noise (14-07).mp4
3 s7 O: s/ R- U+ t! n a │ │ 13 - 4 - Dealing with Overfitting (10-49).mp4- }8 \9 W# B" [3 ^
│ │ 13_handout.pdf- @6 v7 w: V3 {/ v9 W
│ │ 14 - 1 - Regularized Hypothesis Set (19-16).mp4
( N, r$ N3 q9 v' X+ P3 b& n │ │ 14 - 2 - Weight Decay Regularization (24-08).mp4
/ ]8 z7 B1 Q1 `( P% V │ │ 14 - 3 - Regularization and VC Theory (08-15).mp45 _9 w' J2 q- n3 X% L) k
│ │ 14 - 4 - General Regularizers (13-28).mp4
3 }& }; x2 s$ ?1 [ │ │ 14_handout.pdf9 Q6 B3 T2 t5 G+ u D3 x) q
│ │ 15 - 1 - Model Selection Problem (16-00).mp4/ M; a; `6 q# Q$ P% o
│ │ 15 - 2 - Validation (13-24).mp4
4 t$ A# P$ Q' T: B g* p │ │ 15 - 3 - Leave-One-Out Cross Validation (16-06).mp4+ b7 l/ B! H- A6 `' C# s
│ │ 15 - 4 - V-Fold Cross Validation (10-41).mp4
8 d, K1 W4 b8 V+ m5 k │ │ 15_handout.pdf
( C) N- L0 A: O& ]% t │ │ 16 - 1 - Occam-'s Razor (10-08).mp4, [ F, \7 z5 I R
│ │ 16 - 2 - Sampling Bias (11-50).mp4( ^2 k, V. y4 X! j2 f7 A$ B6 u
│ │ 16 - 3 - Data Snooping (12-28).mp4
- s P. m. c+ h: N) p │ │ 16 - 4 - Power of Three (08-49).mp4( h( v( \9 m, A- o
│ │ 16_handout.pdf
( a! b5 G7 w* l │ │ 2 - 1 - Perceptron Hypothesis Set (15-42).mp4* u* T6 o4 B5 r* Q, e: E1 R- O
│ │ 2 - 2 - Perceptron Learning Algorithm (PLA) (19-46).mp4
$ c2 p: k; o) e6 @4 Y& P# _ │ │ 2 - 3 - Guarantee of PLA (12-37).mp4, J9 D; P& |0 M* d
│ │ 2 - 4 - Non-Separable Data (12-55).mp45 W, i0 G% `: Z1 V# I0 C
│ │ 3 - 1 - Learning with Different Output Space (17-26).mp4% k0 Y7 w6 p9 b7 J' O1 n, D6 X( j
│ │ 3 - 2 - Learning with Different Data Label (18-12).mp49 ~! W+ ~; |/ N! G. Y2 o
│ │ 3 - 3 - Learning with Different Protocol (11-09).mp4
9 @% W) H/ A" h7 [ │ │ 3 - 4 - Learning with Different Input Space (14-13).mp46 y' ~5 J s, K* z- s; P' x
│ │ 4 - 1 - Learning is Impossible- (13-32).mp4$ ?( a+ }! V# s
│ │ 4 - 2 - Probability to the Rescue (11-33).mp4
! v7 D# r) b: I% n& U2 N8 M+ \ │ │ 4 - 3 - Connection to Learning (16-46).mp4$ y2 a% Q) J: L8 U
│ │ 4 - 4 - Connection to Real Learning (18-06).mp4) [" U% P3 b& i; {
│ │ 5 - 1 - Recap and Preview (13-44).mp4
! a0 Q5 c( f4 y0 g0 s │ │ 5 - 2 - Effective Number of Lines (15-26).mp4
, `! R$ q) F3 [/ y │ │ 5 - 3 - Effective Number of Hypotheses (16-17).mp4
/ e# ]* l, F! ~' y, V+ C7 U5 o │ │ 5 - 4 - Break Point (07-44).mp4 S# V% h4 F/ B1 R9 t, R1 O
│ │ 6 - 1 - Restriction of Break Point (14-18).mp4- a# v" u9 Z# f7 d5 \
│ │ 6 - 2 - Bounding Function- Basic Cases (06-56).mp4
/ F# s2 d1 K4 j8 [ │ │ 6 - 3 - Bounding Function- Inductive Cases (14-47).mp42 P7 E- ~) T# p! R; P
│ │ 6 - 4 - A Pictorial Proof (16-01).mp4. `0 d6 S' A0 Z1 I, }
│ │ 7 - 1 - Definition of VC Dimension (13-10).mp4* s4 P1 W+ A' e0 t2 E) l
│ │ 7 - 2 - VC Dimension of Perceptrons (13-27).mp4 i5 X. b2 l# c' b# W3 f- p
│ │ 7 - 3 - Physical Intuition of VC Dimension (6-11).mp4# W& g" z' f& ~- N5 }; f/ W9 \
│ │ 7 - 4 - Interpreting VC Dimension (17-13).mp4, I8 _/ g. T& E, i; Y0 c; M/ [$ m
│ │ 8 - 1 - Noise and Probabilistic Target (17-01).mp4
# U `/ v! `; c2 ^( f- l+ i m8 y# p │ │ 8 - 2 - Error Measure (15-10).mp4' _$ I0 Z! [0 a! O% n6 ]9 |
│ │ 8 - 3 - Algorithmic Error Measure (13-46).mp4* g1 j* \. z B# E& H- x
│ │ 8 - 4 - Weighted Classification (16-54).mp4
" V: ^ j1 {3 X3 y │ │ 9 - 1 - Linear Regression Problem (10-08).mp4
7 R" G: z; E/ G! ~3 ] │ │ 9 - 2 - Linear Regression Algorithm (20-03).mp4+ F" y O f1 s: z8 b
│ │ 9 - 3 - Generalization Issue (20-34).mp4! y8 G) g. s+ C" t
│ │ 9 - 4 - Linear Regression for Binary Classification (11-23).mp46 r" T# y, R6 V
│ │
6 o# Q, m5 v5 X3 H6 Y& T │ ├─机器学习的基石9 \9 V! C7 s1 G+ K* a7 k
│ │ 1 - 1 - Course Introduction (10-58).mp4
& |; \* G! t! z9 `1 I$ x │ │ 1 - 2 - What is Machine Learning (18-28).mp4
: ^" A C0 [2 ^9 [' Y* k │ │ 1 - 3 - Applications of Machine Learning (18-56).mp4, F$ b; Y4 `0 ?7 \ `* H9 B- S7 `
│ │ 1 - 4 - Components of Machine Learning (11-45).mp46 m3 J! U. |2 a6 a
│ │ 1 - 5 - Machine Learning and Other Fields (10-21).mp4
' r) b" x! x6 x! Y │ │ 10 - 1 - Logistic Regression Problem (14-33).mp4
2 E% q: ?5 M) V0 c, T7 P( \) }# S& l │ │ 10 - 2 - Logistic Regression Error (15-58).mp4( f- B7 h! L% {" p6 T
│ │ 10 - 3 - Gradient of Logistic Regression Error (15-38).mp4 N4 M0 \: R) L$ \$ v% i
│ │ 10 - 4 - Gradient Descent (19-18).mp4
9 h3 ]( r+ U! Y4 z' u3 h; b1 f │ │ 11 - 1 - Linear Models for Binary Classification (21-35).mp4) E0 M) U2 H* W4 g
│ │ 11 - 2 - Stochastic Gradient Descent (11-39).mp48 U8 g' A6 N9 B1 _4 l. C
│ │ 11 - 3 - Multiclass via Logistic Regression (14-18).mp4: {2 l5 s# w3 j+ _
│ │ 11 - 4 - Multiclass via Binary Classification (11-35).mp41 x8 \4 _) S" [1 W7 i$ R% }
│ │ 12 - 1 - Quadratic Hypothesis (23-47).mp4, M- S# \+ N/ H4 ? W# a
│ │ 12 - 2 - Nonlinear Transform (09-52).mp49 L1 e2 v _; _1 v2 d( o+ b- {
│ │ 12 - 3 - Price of Nonlinear Transform (15-37).mp4! c4 i/ O& K0 H/ }( S r) z. g" u
│ │ 12 - 4 - Structured Hypothesis Sets (09-36).mp45 D2 S; h% g O9 q; i. j
│ │ 13 - 1 - What is Overfitting- (10-45).mp4
# S- N; k4 @% _1 ?; T2 S │ │ 13 - 2 - The Role of Noise and Data Size (13-36).mp47 t* i% Q6 `+ c3 U% Z/ C) e
│ │ 13 - 3 - Deterministic Noise (14-07).mp4
* { c ?' K/ N5 u0 s: o │ │ 13 - 4 - Dealing with Overfitting (10-49).mp4% N4 K3 S: F9 r0 _
│ │ 14 - 1 - Regularized Hypothesis Set (19-16).mp4
+ s( A) S" X/ B$ M) F │ │ 14 - 2 - Weight Decay Regularization (24-08).mp4. G" {! u7 E+ h7 L7 p7 _
│ │ 14 - 3 - Regularization and VC Theory (08-15).mp4
- \; h" v2 }) K2 v# H; B$ [ │ │ 14 - 4 - General Regularizers (13-28).mp4, Y3 ~( `. {* t- C0 E% |, Y
│ │ 15 - 1 - Model Selection Problem (16-00).mp47 U8 J2 O# q% n( D+ Q
│ │ 15 - 2 - Validation (13-24).mp4% S7 A' T; U7 [5 w9 N
│ │ 15 - 3 - Leave-One-Out Cross Validation (16-06).mp4
4 Y6 d3 @$ R N- e+ y) i │ │ 15 - 4 - V-Fold Cross Validation (10-41).mp4
( O% h. T3 M$ V, o9 v' b. a │ │ 16 - 1 - Occam-'s Razor (10-08).mp4: e, U3 p% x2 h, E7 @5 O
│ │ 16 - 2 - Sampling Bias (11-50).mp4( g7 e+ E8 q9 A
│ │ 16 - 3 - Data Snooping (12-28).mp4
8 F1 q6 i, J8 Q) M- s4 C% `% Y │ │ 16 - 4 - Power of Three (08-49).mp4; R& d: u+ q5 F& x4 E
│ │ 2 - 1 - Perceptron Hypothesis Set (15-42).mp4
7 b( Q+ r; P, w8 \8 R4 o1 e │ │ 2 - 2 - Perceptron Learning Algorithm (PLA) (19-46).mp4
6 H0 g, Z/ s1 o3 k │ │ 2 - 3 - Guarantee of PLA (12-37).mp4
1 j3 }' R, N' E: Z │ │ 2 - 4 - Non-Separable Data (12-55).mp4
# t8 D0 D1 K3 l: ]# r: l │ │ 3 - 1 - Learning with Different Output Space (17-26).mp4
9 L5 G$ n! t- s& b │ │ 3 - 2 - Learning with Different Data Label (18-12).mp4
) {( k8 P( }+ k# m" C) \3 g │ │ 3 - 3 - Learning with Different Protocol (11-09).mp45 Y8 ]/ C% T) r( ^6 S4 M
│ │ 3 - 4 - Learning with Different Input Space (14-13).mp4! j6 n, d1 L( j. \2 \3 \: q7 M
│ │ 4 - 1 - Learning is Impossible- (13-32).mp4
$ n# \0 C0 g( f5 Z j5 X, v │ │ 4 - 2 - Probability to the Rescue (11-33).mp43 v" I6 t- Z9 D7 m
│ │ 4 - 3 - Connection to Learning (16-46).mp4( p @5 k9 L# q0 z- d I- e% z: A u
│ │ 4 - 4 - Connection to Real Learning (18-06).mp4
% M5 ?# S0 _8 V/ j' k" W c4 U- M │ │ 5 - 1 - Recap and Preview (13-44).mp4
, T/ c! Y7 B2 }- [7 r$ U, ^( u │ │ 5 - 2 - Effective Number of Lines (15-26).mp4 ~! `$ n o- f. Q- d5 w
│ │ 5 - 3 - Effective Number of Hypotheses (16-17).mp4
( p g: V, s; n" T │ │ 5 - 4 - Break Point (07-44).mp4
9 o; x) V: x% S │ │ 6 - 1 - Restriction of Break Point (14-18).mp4
7 r# L. P' r( H, P; l, E │ │ 6 - 2 - Bounding Function- Basic Cases (06-56).mp4& G; ~# S3 O- v O- v9 D
│ │ 6 - 3 - Bounding Function- Inductive Cases (14-47).mp4: G6 ]7 Q8 X; s, n5 s( X
│ │ 6 - 4 - A Pictorial Proof (16-01).mp4
2 W5 O' l9 P3 k; b5 I: z y │ │ 7 - 1 - Definition of VC Dimension (13-10).mp4
* i" r# _5 x* c' t, z" E │ │ 7 - 2 - VC Dimension of Perceptrons (13-27).mp4
1 S! h; ~) H* d1 m+ q │ │ 7 - 3 - Physical Intuition of VC Dimension (6-11).mp4
$ u5 X, `( @& c6 w* @ │ │ 7 - 4 - Interpreting VC Dimension (17-13).mp42 i% |( M) _# J! U: O
│ │ 8 - 1 - Noise and Probabilistic Target (17-01).mp4. T8 V; p% l- x; y1 Y+ _
│ │ 8 - 2 - Error Measure (15-10).mp49 |+ a6 v7 @* W1 q0 A
│ │ 8 - 3 - Algorithmic Error Measure (13-46).mp4; { \6 R' B, X$ E& m7 B; ?
│ │ 8 - 4 - Weighted Classification (16-54).mp4
5 q" x; j' C5 S8 b1 h- h1 T │ │ 9 - 1 - Linear Regression Problem (10-08).mp48 }* q ~# Z7 S
│ │ 9 - 2 - Linear Regression Algorithm (20-03).mp49 M1 {- ~. N$ H! x# Z
│ │ 9 - 3 - Generalization Issue (20-34).mp4
: x8 M5 y& m! d │ │ 9 - 4 - Linear Regression for Binary Classification (11-23).mp4
1 [+ G! |& K4 F% ~, _. q │ │ lecture_slides-01_handout.pdf
2 Y. _5 ~( ]4 v3 W* j: M- h │ │ lecture_slides-02_handout.pdf
/ l1 ^" ?/ R( `/ o4 r │ │ lecture_slides-03_handout.pdf
/ W- S2 E: T% k9 j │ │ lecture_slides-04_handout.pdf" y: V: I3 E# S5 m B8 }2 x
│ │ lecture_slides-05_handout.pdf4 V y1 O! O" V! n/ F+ |
│ │ lecture_slides-06_handout.pdf! F- G# t- M/ j9 _( l; P4 J
│ │ lecture_slides-07_handout.pdf
; v ]* k. L, [& Y0 F3 P+ ^0 o │ │ lecture_slides-08_handout.pdf; g7 i2 M% t$ g
│ │ lecture_slides-09_handout.pdf
) r2 Q$ u0 f! c │ │ lecture_slides-10_handout.pdf
9 v f3 x/ P9 `2 B* i1 d* u. O* w │ │ lecture_slides-11_handout.pdf ]6 U# D6 O% ~# \7 \- b0 {
│ │ lecture_slides-12_handout.pdf: A4 _7 \8 x) o" L6 E: A3 }
│ │ lecture_slides-13_handout.pdf5 w2 H6 b8 Z. s0 D7 n2 a" n
│ │ lecture_slides-14_handout.pdf
% `8 d3 X$ T4 P1 m$ O1 M! z% a9 Y │ │ lecture_slides-15_handout.pdf
2 m( T: |, p/ |- M! K2 z │ │ lecture_slides-16_handout.pdf
+ G# I- \2 P; _ │ │
, S: h0 M+ a1 l3 o% Y1 m1 a1 _ │ └─機器學習基石
- ^# L; d5 Y0 i │ ├─01_-_The_Learning_Problem
% O& r! h9 t9 E+ k │ │ 01_Course_Introduction_10-58.mp40 l! D! ^# V W4 W
│ │ 01_Course_Introduction_10-58.pdf
6 `* C( u `, Q/ V' D7 e0 C │ │ 02_What_is_Machine_Learning_18-28.mp4* z X" S1 g3 l, ^8 I) q
│ │ 03_Applications_of_Machine_Learning_18-56.mp4, Z9 \) ^; _' F; K7 X
│ │ 04_Components_of_Machine_Learning_11-45.mp41 J( N: W+ b9 {. V8 { ~- A) n
│ │ 05_Machine_Learning_and_Other_Fields_10-21.mp46 [# k$ a# m4 u# Y' p: R
│ │ 6 T% A+ i$ v$ t2 X! k! A
│ ├─02_-_Learning_to_Answer_Yes-No
/ h( X i! q3 M' J$ R │ │ 01_Perceptron_Hypothesis_Set_15-42.mp4
' I. g$ c! d j5 Y │ │ 01_Perceptron_Hypothesis_Set_15-42.pdf
; \, r) b% v) k │ │ 02_Perceptron_Learning_Algorithm_PLA_19-46.mp42 t% P5 T# ^$ ?" Z/ v- z% G2 {
│ │ 03_Guarantee_of_PLA_12-37.mp4! }& ?! U+ L8 M# r# t \
│ │ 04_Non-Separable_Data_12-55.mp4% U& l4 |0 B, o5 {# [
│ │ 1 L+ X8 b' Y" \8 c S
│ ├─03_-_Types_of_Learning) E8 ]( E$ A* ^8 N) u
│ │ 01_Learning_with_Different_Output_Space_17-26.mp4
( o3 C+ U; I$ g+ _" ~3 r │ │ 01_Learning_with_Different_Output_Space_17-26.pdf
% ?4 e0 O0 B# g6 n4 }# f3 Z │ │ 02_Learning_with_Different_Data_Label_18-12.mp4- M g' R# j+ k9 s5 m. T7 `. t
│ │ 03_Learning_with_Different_Protocol_11-09.mp4
3 U" F { D. o/ _: A' o │ │ 04_Learning_with_Different_Input_Space_14-13.mp4% c: T/ y5 [ X8 ?9 W' H" X
│ │ ; \9 }" j6 C3 d2 G' y; Y7 Q3 J5 w# W
│ ├─04_-_Feasibility_of_Learning
W2 ^0 M# l) Q K W; A. ]% L │ │ 01_Learning_is_Impossible_13-32.mp46 T; C" S6 n, C+ Z
│ │ 01_Learning_is_Impossible_13-32.pdf
3 Q) ~$ r8 \5 t& G @/ E │ │ 02_Probability_to_the_Rescue_11-33.mp4
- [& l" q! q2 e │ │ 03_Connection_to_Learning_16-46.mp4 k5 [% ^6 g* B) _9 l( J
│ │ 04_Connection_to_Real_Learning_18-06.mp42 d8 E! K! N9 ?( {
│ │ , a+ `! f: g" g7 d' R
│ ├─05_-_Training_versus_Testing
; Z- r/ _" k/ X2 X( C │ │ 01_Recap_and_Preview_13-44.mp4* w) F( V/ N m8 h
│ │ 01_Recap_and_Preview_13-44.pdf- C+ x0 P: g7 ~, M4 g
│ │ 02_Effective_Number_of_Lines_15-26.mp4' k! A: F0 q& k7 ^3 J
│ │ 03_Effective_Number_of_Hypotheses_16-17.mp4* O5 {3 Z% K0 o. p# A
│ │ 04_Break_Point_07-44.mp41 f. X7 R4 C% E+ V
│ │ / L% r/ ]1 I8 `! N) n' {
│ ├─06_-_Theory_of_Generalization% ~$ f; u( j/ s7 x3 z
│ │ 01_Restriction_of_Break_Point_14-18.mp4
! X! h! _* H* O0 C/ o: k T │ │ 01_Restriction_of_Break_Point_14-18.pdf
5 P+ C2 l0 I6 }! z& D │ │ 02_Bounding_Function-_Basic_Cases_06-56.mp4& V! {8 Z0 b+ H7 }8 Y
│ │ 03_Bounding_Function-_Inductive_Cases_14-47.mp4' e! ]/ c! l( d4 \0 |- w2 t) l
│ │ 04_A_Pictorial_Proof_16-01.mp40 G4 ~1 z- W) M9 r2 C# O
│ │
+ Q+ H1 h* x" N7 Y5 C; U │ ├─07_-_The_VC_Dimension2 n: u: C: P o5 |" [& l
│ │ 01_Definition_of_VC_Dimension_13-10.mp4: o' m W" D& b% @0 |
│ │ 01_Definition_of_VC_Dimension_13-10.pdf, Z# l- {0 _! z
│ │ 02_VC_Dimension_of_Perceptrons_13-27.mp4- F; U8 A5 i8 U0 v8 m
│ │ 03_Physical_Intuition_of_VC_Dimension_6-11.mp4 l* R) E& A+ d
│ │ 04_Interpreting_VC_Dimension_17-13.mp4
: p+ }4 S' H4 e+ u9 t' j │ │ * d8 ]2 d" k5 m
│ ├─08_-_Noise_and_Error
; g4 ]2 J! U8 x4 c1 z5 Z4 k │ │ 01_Noise_and_Probabilistic_Target_17-01.mp4# H! h( h0 k" F# U
│ │ 01_Noise_and_Probabilistic_Target_17-01.pdf' w& A y' W; |$ ]9 q( l R5 B
│ │ 02_Error_Measure_15-10.mp4
2 q$ F. r7 x+ L. L! z3 Q5 \ │ │ 03_Algorithmic_Error_Measure_13-46.mp4) k: o' E8 r& g# m5 ~" [# T5 D
│ │ 04_Weighted_Classification_16-54.mp45 A+ y, V; T$ r4 _
│ │
5 l% s$ v: q' n; |5 Q( |! y/ ? │ ├─09_-_Linear_Regression* N/ [' m- p4 W* W: y( m6 A4 H/ ?
│ │ 01_Linear_Regression_Problem_10-08.mp4
$ P9 m3 a. n. z0 T$ n; U V │ │ 01_Linear_Regression_Problem_10-08.pdf$ y) |: }' N: n
│ │ 02_Linear_Regression_Algorithm_20-03.mp48 W# d2 ?* X' x1 E7 K- A
│ │ 03_Generalization_Issue_20-34.mp4
# q: _7 r! a+ r. L% S g9 | │ │ 04_Linear_Regression_for_Binary_Classification_11-23.mp4
/ B8 F) P* `, }0 A. G │ │ - ~, y* T- i) M/ v1 R
│ ├─10_-_Logistic_Regression
* `4 ?- b+ [, h6 H( h, m │ │ 01_Logistic_Regression_Problem_14-33.mp4
/ W. \8 I6 H' _$ z │ │ 01_Logistic_Regression_Problem_14-33.pdf' C! D8 D) ?+ Q3 K" M
│ │ 02_Logistic_Regression_Error_15-58.mp4
' F/ R; D$ V- |2 L+ m7 j │ │ 03_Gradient_of_Logistic_Regression_Error_15-38.mp4
/ B1 {0 S7 T/ o7 A- Q' @) u │ │ 04_Gradient_Descent_19-18.mp4* `6 a/ g/ t2 Y; f' A, c! _& K
│ │
; }# _$ H& i- | │ ├─11_-_Linear_Models_for_Classification
6 W$ q, `* g2 d" i │ │ 01_Linear_Models_for_Binary_Classification_21-35.mp4
4 e4 [ z0 Z8 w* u │ │ 01_Linear_Models_for_Binary_Classification_21-35.pdf
, I& t/ \1 d0 s. [ │ │ 02_Stochastic_Gradient_Descent_11-39.mp4
) H) d3 s# N! C& ]* b* u) @* r7 n. v │ │ 03_Multiclass_via_Logistic_Regression_14-18.mp4, i$ ]3 s' r2 s' Q; ]
│ │ 04_Multiclass_via_Binary_Classification_11-35.mp4
3 k: W& Y' N5 v& ?) u │ │ . Y2 _! d# k% S9 V: Z& F- ~( |
│ ├─12_-_Nonlinear_Transformation2 c9 S9 K) _. h4 j p# o
│ │ 01_Quadratic_Hypothesis_23-47.mp4
0 o3 u$ {& ^5 X- n; O │ │ 01_Quadratic_Hypothesis_23-47.pdf3 }: w2 |- n( `
│ │ 02_Nonlinear_Transform_09-52.mp4" l* T' ~( J+ ?# v/ |/ \
│ │ 03_Price_of_Nonlinear_Transform_15-37.mp42 ^: q" e& B9 `6 r& ~2 b
│ │ 04_Structured_Hypothesis_Sets_09-36.mp4
' A+ E) L- e- e8 Z# G" \5 Z) e: C& }+ y │ │ - r( c. S( d* \) w! N6 K
│ ├─13_-_Hazard_of_Overfitting
3 k% {6 E0 h' T5 Q& r8 ^ │ │ 01_What_is_Overfitting_10-45.mp4 q5 [+ S% ^+ {. U: s% H
│ │ 01_What_is_Overfitting_10-45.pdf7 }! p8 N. }8 G4 t- c4 r( x
│ │ 02_The_Role_of_Noise_and_Data_Size_13-36.mp40 U& z# l3 ?' r X$ I/ o
│ │ 03_Deterministic_Noise_14-07.mp42 B* ?0 y3 {/ J+ A2 C
│ │ 04_Dealing_with_Overfitting_10-49.mp4+ ^/ h; r: I3 M4 D2 O5 M# L
│ │ 9 J1 |; F5 s. H" e0 h2 m) {; ~
│ ├─14_-_Regularization
0 e W5 M' W% P. G │ │ 01_Regularized_Hypothesis_Set_19-16.mp4
. t# O$ e0 o1 q9 z% | │ │ 01_Regularized_Hypothesis_Set_19-16.pdf& w2 E: N& f3 G" w4 G
│ │ 02_Weight_Decay_Regularization_24-08.mp4
, y1 U! O! A5 y5 }4 f; f( z/ i7 k* P │ │ 03_Regularization_and_VC_Theory_08-15.mp4
. R# S" {7 [) h │ │ 04_General_Regularizers_13-28.mp4; Z# i* x; Y# ~& x0 z$ i
│ │ J3 n G( m$ o+ v s ^# ?/ E
│ ├─15_-_Validation
; t3 y g" N p% R0 p# J. g │ │ 01_Model_Selection_Problem_16-00(437).mp4
, w1 v% F e3 z6 K& I2 } │ │ 01_Model_Selection_Problem_16-00.pdf+ j7 P# _% } _7 n
│ │ 02_Validation_13-24.mp4. t( Q1 r! V7 \
│ │ 03_Leave-One-Out_Cross_Validation_16-06.mp4
1 J2 I( ?) G7 B3 T' X+ D- m │ │ 04_V-Fold_Cross_Validation_10-41.mp48 b; s& D' L! ^0 B0 t( d$ T
│ │ 5 G, J( O1 M) E, ^9 C. ~) j* \
│ └─16_-_Three_Learning_Principles) y& u. j& g( G) O/ m' u6 r
│ 01_Occams_Razor_10-08.mp4
* V" t: a, N, Y Y/ M, [ │ 01_Occams_Razor_10-08.pdf* U4 |1 t# g! p/ q5 K3 X
│ 02_Sampling_Bias_11-50.mp4
. z+ X. G) \( d3 p# _' W │ 03_Data_Snooping_12-28.mp4- L) B s- Q, |% \! P+ h* [
│ 04_Power_of_Three_08-49.mp4& L5 F+ n$ v- \. F; {' B; W
│ # v/ t+ X: s% D ~2 E+ g
├─004_机器学习技法
# r, L: n/ w4 A │ └─004_机器学习技法8 N! A. r2 O5 o' {9 `" {5 R( D, D, s
│ └─機器學習技法3 L/ ^2 C, c; i6 P; W3 @4 e6 C
│ │ 下载说明.txt
# Q; Q# D& P9 S3 [9 C │ │ 关注我们.png
+ Q, H( r( c& f/ G% ?0 N( ` │ │ 攻城狮论坛=网络技术+编程视频.url
3 Q; ^' `* S0 s1 R( e' Z$ X │ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt
/ M" y5 }0 ?! n) j8 [& V │ │
5 H* B8 a) D1 H6 L4 [0 k │ ├─01_Linear_Support_Vector_Machine7 |) ]$ W; n3 O6 l# t# h
│ │ 01_Course_Introduction_4-07.mp47 j+ ~# _, k/ z% K& L0 c5 A1 \ S
│ │ 01_Course_Introduction_4-07.pdf
+ A8 J" V, }6 N6 ~$ | │ │ 02_Large-Margin_Separating_Hyperplane_14-17.mp4: q J8 W& z# Z2 q+ r: r
│ │ 03_Standard_Large-Margin_Problem_19-16.mp4, {) A/ Z2 v" D- P
│ │ 04_Support_Vector_Machine_15-33.mp4
3 m* s& Q6 ^; y; X& S8 j6 D; U │ │ 05_Reasons_behind_Large-Margin_Hyperplane_13-31.mp4 S6 @2 p3 H* j' `# F2 S/ [: Q5 o! ~
│ │ ( b8 E W' t' f$ R+ f$ q$ m6 N
│ ├─02_Dual_Support_Vector_Machine
' [+ ~$ ?5 i' h, u2 N* a │ │ 01_Motivation_of_Dual_SVM_15-54.mp4
" @. r3 X* p+ [! N& a/ f- p8 e% d1 L │ │ 01_Motivation_of_Dual_SVM_15-54.pdf+ |- {4 _ j( `4 ^/ D
│ │ 02_Lagrange_Dual_SVM_18-50.mp4
# T, t0 i" q+ U% |0 @$ @ │ │ 03_Solving_Dual_SVM_14-19.mp41 d7 R U) M' Y
│ │ 04_Messages_behind_Dual_SVM_11-18.mp4' O) G9 d# z% R: ~2 v( j6 B& Z
│ │ 7 c- i' }2 X0 [
│ ├─03_Kernel_Support_Vector_Machine8 f7 n4 S4 s$ q# ?5 }
│ │ 01_Kernel_Trick_20-23.mp48 O& Y, J! ]* x
│ │ 01_Kernel_Trick_20-23.pdf0 E# v: X' ^" V
│ │ 02_Polynomial_Kernel_12-16.mp4 {* F/ U4 v. N8 h+ _+ h) {
│ │ 03_Gaussian_Kernel_14-43.mp49 w8 H K0 Y/ Z K1 v" Y+ `" `
│ │ 04_Comparison_of_Kernels_13-35.mp46 p6 d! V& W* a T' S* r
│ │
( y* A' i" j7 b8 F1 F$ w, m1 E │ ├─04_Soft-Margin_Support_Vector_Machine
% K5 t) V! V1 r" C) A, G+ z │ │ 01_Motivation_and_Primal_Problem_14-27.mp42 W3 B% [& `' Y( y
│ │ 01_Motivation_and_Primal_Problem_14-27.pdf0 ]( M% t P* M/ G3 v0 w$ n! o
│ │ 02_Dual_Problem_7-38.mp4
; o1 T$ d" V6 N% X; N7 r% W: W* } │ │ 03_Messages_behind_Soft-Margin_SVM_13-44.mp4
( `$ E" i L9 E+ O3 _3 w* D │ │ 04_Model_Selection_9-57.mp4, p* j2 V+ w/ R S0 Z) K
│ │
( b: h/ F; h5 @. W5 |. |9 A │ ├─05_Kernel_Logistic_Regression1 N9 P8 X. _2 c; I
│ │ 01_Soft-Margin_SVM_as_Regularized_Model_13-40.mp4
2 H# y( I/ w7 X │ │ 01_Soft-Margin_SVM_as_Regularized_Model_13-40.pdf) T# W1 x0 C2 x( d2 ~7 B) q/ I) }
│ │ 02_SVM_versus_Logistic_Regression_10-18.mp4
* N) m7 {- }. Z │ │ 03_SVM_for_Soft_Binary_Classification_9-36.mp4
. f; v* i d9 }0 |% z) c2 ^ │ │ 04_Kernel_Logistic_Regression_16-22.mp4
' E Y/ F9 F5 ~6 ` │ │
: g+ N9 C; A5 t; j0 n% o9 ] │ ├─06_Support_Vector_Regression
r% K: N s) h" O/ i7 v& S │ │ 01_Kernel_Ridge_Regression_17-17.mp4) i% `8 B; q v& u
│ │ 01_Kernel_Ridge_Regression_17-17.pdf
: a7 W+ l+ i1 {( z0 { V0 x │ │ 02_Support_Vector_Regression_Primal_18-44.mp4# Z. ?* B1 g1 C1 _& w
│ │ 03_Support_Vector_Regression_Dual_13-05.mp4" ^$ p8 g- V; u/ f
│ │ 04_Summary_of_Kernel_Models_09-06.mp4" @8 U9 W' l; v+ _4 @
│ │
e; w8 v) {. L8 Q6 u& u+ K │ ├─07_Blending_and_Bagging- F9 S8 R( m, |! a# o+ Z
│ │ 01_Motivation_of_Aggregation_18-54.mp47 i8 @, W' i, Z( G# \& m) _8 d* _
│ │ 01_Motivation_of_Aggregation_18-54.pdf3 d7 Q# v9 m3 j b/ Z8 I6 q7 }7 }
│ │ 02_Uniform_Blending_20-31.mp4
$ N: u" F& b: ^7 s │ │ 03_Linear_and_Any_Blending_16-48.mp4
& [& h7 x4 E; E* b │ │ 04_Bagging_Bootstrap_Aggregation_11-48.mp4" P5 h5 n# Z6 T% r- F$ P+ n
│ │ + q$ W' l4 [: b1 s% c
│ ├─08_Adaptive_Boosting
|% ]; P( {" }* O1 R │ │ 01_Motivation_of_Boosting_12-47.mp4, Z7 S+ C! z1 b3 d
│ │ 01_Motivation_of_Boosting_12-47.pdf
5 `" V' M! ]8 w: c │ │ 02_Diversity_by_Re-weighting_14-28.mp4 F9 j# b: @8 @) r
│ │ 03_Adaptive_Boosting_Algorithm_13-34.mp4/ i1 l5 L4 w. j9 \
│ │ 04_Adaptive_Boosting_in_Action_11-04.mp4' J& m- G( l0 J8 r8 J7 E
│ │ / T5 n9 v, l+ h* Q; [
│ ├─09_Decision_Tree
# s# V( k' r) ` │ │ 01_Decision_Tree_Hypothesis_17-28.mp4
1 S( e& _) `5 i) x8 R# S! ~ │ │ 01_Decision_Tree_Hypothesis_17-28.pdf
! C3 u- @9 U/ f* ^/ [ │ │ 02_Decision_Tree_Algorithm_15-20.mp4# _) o! v: `& c5 e1 I0 \/ @! M& D& S
│ │ 03_Decision_Tree_Heuristics_in_CRT_13-21.mp4
, _$ X( i+ M+ X* m4 F │ │ 04_Decision_Tree_in_Action_8-44.mp4( b6 \* l% u5 O
│ │ 2 P* U T E- w1 u% _& {6 D3 p% A0 G' ?
│ ├─10_Random_Forest0 \5 Q! z6 `, j) Y" R8 r5 E. K
│ │ 01_Random_Forest_Algorithm_13-06.mp4
, Y0 u. W9 D! l │ │ 01_Random_Forest_Algorithm_13-06.pdf
' E) ^% A) U) h. j. v ^, h │ │ 02_Out-Of-Bag_Estimate_12-31.mp4
, L" i. _ B* B. s │ │ 03_Feature_Selection_19-27.mp45 c) ?" l6 T& K
│ │ 04_Random_Forest_in_Action13-28.mp4$ Q6 i7 O# o/ Z$ |2 [+ Z
│ │ 9 u' m0 L. X; D) B8 h
│ ├─11_Gradient_Boosted_Decision_Tree* `9 q7 K7 @0 W
│ │ 01_Adaptive_Boosted_Decision_Tree_15-05.mp4
4 _) L. }8 r9 m- S$ \4 h: p │ │ 01_Adaptive_Boosted_Decision_Tree_15-05.pdf" k/ u: O6 l. e7 E, _
│ │ 02_Optimization_View_of_AdaBoost_27-25.mp4
* z p/ M- H6 }- e7 _ │ │ 03_Gradient_Boosting_18-20.mp4
6 a3 G1 r3 v R& U; U6 s │ │ 04_Summary_of_Aggregation_Models_11-19.mp4" i' J, J, W' P; o! b
│ │ 6 x8 y1 M9 W* L; [
│ ├─12_Neural_Network- l" C) R+ k8 P/ n& s1 M
│ │ 01_Motivation_20-36.mp4! j+ |, o8 H$ O, P* P3 a9 Y+ M9 [
│ │ 01_Motivation_20-36.pdf, O0 A0 D, T" J( w9 p
│ │ 02_Neural_Network_Hypothesis_18-01.mp44 v' X0 }4 S4 t! c& e, y
│ │ 03_Neural_Network_Learning_22-26.mp4
, S/ c2 l% j5 p4 S1 U9 n │ │ 04_Optimization_and_Regularization_17-29.mp4# w( i: E4 j5 N3 z" T6 {6 W
│ │
' k( [+ W. u! b7 P1 F7 E" o/ \% @ │ ├─13_Deep_Learning
7 j+ ^" @; Q5 y4 d! X! @ │ │ 01_Deep_Neural_Network_21-30.mp4
# t S6 ^/ p0 u6 {6 X │ │ 01_Deep_Neural_Network_21-30.pdf+ F6 T% }$ C0 g7 H# ^
│ │ 02_Autoencoder_15-17.mp4
* j+ I% R# v* K* Q$ V0 G │ │ 03_Denoising_Autoencoder_8-30.mp4' l7 E7 k& {; b9 D, ~1 X$ O% t$ ^
│ │ 04_Principal_Component_Analysis_31-20.mp4
2 A* j" V' e" X7 W8 q' I5 i │ │ 9 @/ X$ c0 g! f
│ ├─14_Radial_Basis_Function_Network+ L2 V# w; h# M8 k8 Y9 U* ^( j
│ │ 01_RBF_Network_Hypothesis_12-55.mp4) ]8 I8 D$ a/ v' k
│ │ 01_RBF_Network_Hypothesis_12-55.pdf2 B: V; ~6 @" y0 i1 R
│ │ 02_RBF_Network_Learning_20-08.mp4
/ Z4 v% L4 A8 [. O │ │ 03_k-Means_Algorithm_16-19.mp4
0 I9 S( ^- f! H: Q7 _2 F: M- ?! q │ │ 04_k-Means_and_RBF_Network_in_Action_9-46.mp4- i6 Z% W, J E" {
│ │ $ I2 \0 l( G9 h. @8 z" K/ A5 O
│ ├─15_Matrix_Factorization
. i- y; Z7 @! E$ p6 _4 p │ │ 01_Linear_Network_Hypothesis_20-16.mp4
2 w! v+ ? @) y5 e* w2 T* _2 K │ │ 01_Linear_Network_Hypothesis_20-16.pdf$ ?% o8 S, D3 \: r- i* P9 K$ `- Q
│ │ 02_Basic_Matrix_Factorization_16-32.mp4
9 O6 f, M; C# e# F# ?, Z: | │ │ 03_Stochastic_Gradient_Descent_12-22.mp4
6 X0 y f* `+ ~ │ │ 04_Summary_of_Extraction_Models_9-12.mp4. u( G" M5 z6 C9 g
│ │
1 Q5 b$ @8 b: X- s% _- C │ └─16_Finale# P" |& k, F% q4 I
│ 01_Feature_Exploitation_Techniques_16-11.mp45 f. i; l+ |8 K& ]7 |9 \& ^4 V
│ 01_Feature_Exploitation_Techniques_16-11.pdf0 @$ I! w% T! t8 A% z3 F; i
│ 02_Error_Optimization_Techniques_8-40.mp4/ w- m" m- v: m3 H& \) K; I
│ 03_Overfitting_Elimination_Techniques_6-44.mp46 ?+ S& ^0 O1 ?! ~1 ]2 f- }
│ 04_Machine_Learning_in_Action_12-59.mp4
% l2 O1 V$ {7 r$ f9 d8 G │ 9 |6 w& E4 S9 p( B
├─005_Neural Networks for Machine Learning
$ A& U' x* f6 R. t3 T) W │ └─005_Neural Networks for Machine Learning( X9 ^$ ]! u: j" \9 `: u: }7 j
│ │ 下载说明.txt1 n7 l; r3 [! k% C: x& |
│ │ 关注我们.png, u5 c. l$ n# q& d. U: {5 G* ?
│ │ 攻城狮论坛=网络技术+编程视频.url
q6 \" O r5 Z' [1 c: h │ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt9 \& E1 L: I, [/ x
│ │
: C/ j( `5 }; `9 \' O# F* X │ ├─hinton-ml
: t- D; O+ R0 l& d4 w │ │ 1.Why do we need machine learning) G5 j2 [6 R) d8 g$ ?0 p
│ │ 1.Why do we need machine learning.mp4
3 z6 }1 L4 \3 @: G# ~- E; t6 L │ │ 10.What perceptrons can't do [15 min].mp4/ q$ g# U6 E" H g: Z. w
│ │ 10.What perceptrons can't do [15 min].srt
# M9 x. l: ]- u$ \$ l │ │ 11.Learning the weights of a linear neuron [12 min].mp4! e' L5 ^2 }1 I% q2 c$ L4 f* m" M
│ │ 11.Learning the weights of a linear neuron [12 min].srt4 G: f) g7 w1 ^; T- e
│ │ 12.The error surface for a linear neuron [5 min].mp45 |; S; [% [2 t: x8 s( O/ A
│ │ 12.The error surface for a linear neuron [5 min].srt2 f2 S! {! V9 i1 \$ W v
│ │ 13.Learning the weights of a logistic output neuron [4 min].mp4
! \9 u/ y$ [( j! D9 |1 k# [5 L │ │ 13.Learning the weights of a logistic output neuron [4 min].srt
H3 R ~; m5 V) s- s │ │ 14.The backpropagation algorithm [12 min].mp4' ^% ?5 J# Z% x9 q7 u* {4 Y* Q
│ │ 14.The backpropagation algorithm [12 min].srt
`4 y& a* n7 w │ │ 15.Using the derivatives computed by backpropagation [10 min].mp4
* m- u5 p! }; S4 Z │ │ 15.Using the derivatives computed by backpropagation [10 min].srt5 C+ B: [4 [+ v& s7 P! H3 t d
│ │ 16.Learning to predict the next word [13 min].mp4
# ^! L8 y4 X& I- u │ │ 16.Learning to predict the next word [13 min].srt+ m5 g7 C2 u* V% k& o! B( _
│ │ 17.A brief diversion into cognitive science [4 min].mp4
" k' E) b0 }& ?7 E7 P │ │ 17.A brief diversion into cognitive science [4 min].srt
& b5 L$ z2 W; ]' t5 Y │ │ 19.Neuro-probabilistic language models [8 min].mp4+ @ ?4 T2 X$ X! f( z3 t* K+ P
│ │ 19.Neuro-probabilistic language models [8 min].srt
( F- u0 [! p6 C0 @4 U0 [ │ │ 2.What are neural networks
8 W, j, [5 r5 d7 V) } │ │ 2.What are neural networks.mp43 x9 z4 ^# a6 k ^
│ │ 20.Ways to deal with the large number of possible outputs [15 min].mp4( `* x1 s( y! B) w3 }( ~
│ │ 20.Ways to deal with the large number of possible outputs [15 min].srt
% X6 S3 r: X8 s │ │ 21.Why object recognition is difficult [5 min].mp4; U+ }& Z2 A: {* |" B# b
│ │ 21.Why object recognition is difficult [5 min].srt0 B8 K. k. B% `3 l, o0 ^
│ │ 22.Achieving viewpoint invariance [6 min].mp4: \! f5 D+ v0 s, }! ?4 ^3 w& ]
│ │ 22.Achieving viewpoint invariance [6 min].srt
4 N( J1 V, a) I │ │ 23.Convolutional nets for digit recognition [16 min].mp45 r3 T! K0 r, o; k* ~
│ │ 23.Convolutional nets for digit recognition [16 min].srt% _6 j# n4 ?$ Z
│ │ 24.Convolutional nets for object recognition [17min].mp4( a: r/ n k9 G) e
│ │ 24.Convolutional nets for object recognition [17min].srt
2 m/ [# m4 K/ J' l1 F │ │ 25.Overview of mini-batch gradient descent.mp49 L3 ~2 i: @+ G% G! h
│ │ 25.Overview of mini-batch gradient descent.srt9 {# e% l; X+ o$ Q1 R; N, [
│ │ 26.A bag of tricks for mini-batch gradient descent.mp4( B7 H z8 U% @7 W: ~* r3 S
│ │ 26.A bag of tricks for mini-batch gradient descent.srt8 i, {4 Q0 @7 V
│ │ 27.The momentum method.mp4
( {+ \8 A; Q. D │ │ 27.The momentum method.srt
1 }. V* a' h7 X) U% z4 a$ [ │ │ 28.Adaptive learning rates for each connection.mp4
7 S4 d9 F5 J' k2 }" ? │ │ 28.Adaptive learning rates for each connection.srt& g4 a! R* W1 h. h
│ │ 3.Some simple models of neurons [8 min].mp4
2 u/ l! [# x4 M* N: c A │ │ 3.Some simple models of neurons [8 min].srt* p" L/ ] ]; `
│ │ 31.Training RNNs with back propagation.mp42 B! }3 O! g" H5 P7 [% Q: L' v
│ │ 31.Training RNNs with back propagation.srt
/ r, V/ x6 p1 H+ s' o! ` │ │ 32.A toy example of training an RNN.mp4
Y3 p& ?0 F" h% R │ │ 32.A toy example of training an RNN.srt
: O5 ?& V- l/ Q: p% l │ │ 33.Why it is difficult to train an RNN.mp4
1 @: [$ r8 @! T" K │ │ 33.Why it is difficult to train an RNN.srt
1 ?( E: @3 A x7 ^ `2 K6 z │ │ 34.Long-term Short-term-memory.mp4
" W$ j( f$ Z5 K* b8 k' y │ │ 34.Long-term Short-term-memory.srt" z2 s. [0 W$ R! m/ v! A9 w
│ │ 35.A brief overview of Hessian Free optimization.mp4+ Y: U5 K) r4 ]0 d; j
│ │ 35.A brief overview of Hessian Free optimization.srt* i( x+ v, m, K0 z8 e
│ │ 37.Learning to predict the next character using HF [12 mins].mp44 j4 p; m3 x; c2 ?% Z+ r* [* e
│ │ 37.Learning to predict the next character using HF [12 mins].srt
: T- h( f. s6 O │ │ 38.Echo State Networks [9 min].mp4
! o$ j! d. g/ \1 p) n6 D5 o' } │ │ 38.Echo State Networks [9 min].srt5 r6 O; w, }0 C" @+ }" q c
│ │ 39.Overview of ways to improve generalization [12 min].mp4
, |0 p8 A0 X! I& N) Y9 z! s/ e │ │ 39.Overview of ways to improve generalization [12 min].srt
- I/ C( H! q5 u$ n% C │ │ 4.A simple example of learning [6 min].mp4
: h: h& |. S) W( d! }% J │ │ 4.A simple example of learning [6 min].srt! t! G a# g" K3 |% \8 L: J
│ │ 40.Limiting the size of the weights [6 min].mp4' e6 H0 z4 S8 A2 a* P
│ │ 40.Limiting the size of the weights [6 min].srt
3 w6 z, b) D( o │ │ 41.Using noise as a regularizer [7 min].mp4; C5 N4 q0 P' i& H
│ │ 41.Using noise as a regularizer [7 min].srt6 M) L3 _2 \2 f! ?
│ │ 42.Introduction to the full Bayesian approach [12 min].mp4
1 V4 y+ m: g6 R │ │ 42.Introduction to the full Bayesian approach [12 min].srt# L0 T5 d1 w) B+ X! |( H2 l4 t& W$ U
│ │ 43.The Bayesian interpretation of weight decay [11 min].mp4
7 G7 Y7 n* x+ t# V0 Y! y │ │ 43.The Bayesian interpretation of weight decay [11 min].srt9 C4 i9 n5 Q# u$ a/ N% {
│ │ 44.MacKay's quick and dirty method of setting weight costs [4 min].mp42 s# Q+ G0 Z& D% o- w4 o# Z' l3 u# v
│ │ 44.MacKay's quick and dirty method of setting weight costs [4 min].srt
' [; o- }' z* S+ J% a6 D. i2 ]& s │ │ 45.Why it helps to combine models [13 min].mp4
. w' `. v7 o. D" ~7 }# }# B T# i: V% X9 \- ? │ │ 45.Why it helps to combine models [13 min].srt4 B7 T& _! ~( z' w) i0 G' S/ x
│ │ 46.Mixtures of Experts [13 min].mp48 o5 h4 o3 N) }# @
│ │ 46.Mixtures of Experts [13 min].srt) K3 y0 g, F" |; w" |# M
│ │ 47.The idea of full Bayesian learning [7 min].mp4
# L( T( V% E" _ │ │ 47.The idea of full Bayesian learning [7 min].srt% z$ @* a5 s+ s( ~+ M! s5 M/ O
│ │ 48.Making full Bayesian learning practical [7 min].mp4; ~2 A; @+ k. ^- E" ~4 ?6 g
│ │ 48.Making full Bayesian learning practical [7 min].srt- v+ d2 `& L Q0 m
│ │ 49.Dropout [9 min].mp43 J2 @/ s1 s# ?. J
│ │ 49.Dropout [9 min].srt
; A: S0 R/ J$ o; { │ │ 5.Three types of learning [8 min].mp4
A7 a# P$ Y# y1 }. t6 n/ o │ │ 5.Three types of learning [8 min].srt
& m" Q) k% c$ s- h* X% D# N2 A/ f& z │ │ 50.Hopfield Nets [13 min].mp4
1 Z r9 N4 {6 }, u6 ^3 x! ? │ │ 50.Hopfield Nets [13 min].srt1 E u9 m2 e( U: p2 J: @- t, Y& K
│ │ 51.Dealing with spurious minima [11 min].mp4. w3 H+ |* L3 o1 M1 y) u! c
│ │ 51.Dealing with spurious minima [11 min].srt' K2 O( B- E( V& U' f8 O
│ │ 52.Hopfield nets with hidden units [10 min].mp4
" u+ [* ?: b: r( ~ │ │ 52.Hopfield nets with hidden units [10 min].srt
5 ]3 m. |8 x8 L( v7 |& T z- } │ │ 53.Using stochastic units to improv search [11 min].mp4% M2 x' Z) j$ ]' t5 l! n
│ │ 53.Using stochastic units to improv search [11 min].srt
# g4 G2 k1 k# A) ]- J │ │ 54.How a Boltzmann machine models data [12 min].mp4( y5 T% u7 f4 @0 `- }6 Y
│ │ 54.How a Boltzmann machine models data [12 min].srt
1 ?2 J1 ]& }/ t7 G7 v* ]) K' r/ D │ │ 55.Boltzmann machine learning [12 min].mp4
; f6 d9 |; h* l/ F# M │ │ 55.Boltzmann machine learning [12 min].srt: o, t6 }5 J9 s- _2 _- F
│ │ 57.Restricted Boltzmann Machines [11 min].mp4
/ P5 ~1 I+ K. s( ?& `# | │ │ 57.Restricted Boltzmann Machines [11 min].srt
, h( _' d+ C, P& e0 k │ │ 58.An example of RBM learning [7 mins].mp4
+ k: O3 X% u% F8 e' k) K' O │ │ 58.An example of RBM learning [7 mins].srt
7 |* w* E6 \4 F5 M( `! ^ │ │ 59.RBMs for collaborative filtering [8 mins].mp4
" V; f8 e8 i; P │ │ 59.RBMs for collaborative filtering [8 mins].srt A( O* p5 d( g3 u/ B3 \
│ │ 6.Types of neural network architectures [7 min].mp4; W' r1 w: r( P; K2 s
│ │ 6.Types of neural network architectures [7 min].srt
6 N- K. N- L; V! s" X: u │ │ 60.The ups and downs of back propagation [10 min].mp46 @% X8 n* R8 { G7 {8 M [- D
│ │ 60.The ups and downs of back propagation [10 min].srt
- _8 S' d& \% a% ~ K7 N │ │ 61.Belief Nets [13 min].mp47 s# b: |2 y* ^$ u2 C5 x) F' I1 O- g
│ │ 61.Belief Nets [13 min].srt2 v# A, ^) t J" q
│ │ 62.Learning sigmoid belief nets [12 min].mp4
: K | O; t& d I8 a" C! l: P │ │ 62.Learning sigmoid belief nets [12 min].srt
; H2 F3 R4 d9 z& H$ B- @, f) O7 e8 | │ │ 63.The wake-sleep algorithm [13 min].mp4
2 e$ }3 Z B* X U8 ^- i │ │ 63.The wake-sleep algorithm [13 min].srt. F! {* Z$ |" C. |5 a
│ │ 64.Learning layers of features by stacking RBMs [17 min].mp48 o4 v: b6 j: u: T Y9 u* R
│ │ 64.Learning layers of features by stacking RBMs [17 min].srt+ a- f9 `! W. P+ G3 Y# o
│ │ 65.Discriminative learning for DBNs [9 mins].mp4: J9 P, A* L# e U. a
│ │ 65.Discriminative learning for DBNs [9 mins].srt6 \. q& q( z/ U9 L. W' J
│ │ 66(1).What happens during discriminative fine-tuning
" l/ E* Z$ H/ _" R, w: W │ │ 66.What happens during discriminative fine-tuning
8 w' z$ {& f' p0 o7 P P, N │ │ 67.Modeling real-valued data with an RBM [10 mins].mp4" h) B2 e! m7 I5 |
│ │ 67.Modeling real-valued data with an RBM [10 mins].srt
( L- R. }/ y2 }5 e5 H) h │ │ 69.From PCA to autoencoders [5 mins].mp4
% t6 n9 y* u, d4 X0 N- d4 O4 M │ │ 69.From PCA to autoencoders [5 mins].srt" D; Z* S, y; a' @6 x; K% ?( V; x
│ │ 70.Deep auto encoders [4 mins].mp4+ N5 Y( \* x: ^8 ~
│ │ 70.Deep auto encoders [4 mins].srt/ K2 e* g5 G+ m+ d
│ │ 71.Deep auto encoders for document retrieval [8 mins].mp4
" `. Q/ J2 u+ n( ~: G │ │ 71.Deep auto encoders for document retrieval [8 mins].srt
+ v2 {( c! C: K' ]& E8 P │ │ 72.Semantic Hashing [9 mins].mp4
' q9 i5 L: C! t# p" ]1 _ │ │ 72.Semantic Hashing [9 mins].srt
9 I. m, c& j( G& W │ │ 73.Learning binary codes for image retrieval [9 mins].mp40 M1 ^" `" n4 I' y8 \8 J* C
│ │ 73.Learning binary codes for image retrieval [9 mins].srt
: t+ ]+ J% P! P" y │ │ 74.Shallow autoencoders for pre-training [7 mins].mp4
) Y+ s5 ?: ^% i$ n │ │ 74.Shallow autoencoders for pre-training [7 mins].srt* v8 h% D7 A+ r# W
│ │ 8.A geometrical view of perceptrons [6 min].mp4
( N& E5 c5 O2 h" x5 g │ │ 8.A geometrical view of perceptrons [6 min].srt1 J3 C+ C$ a( Q2 I1 ?; i* t
│ │ 9.Why the learning works [5 min].mp4: O' V1 H, \$ H2 x, K6 K5 q
│ │ 9.Why the learning works [5 min].srt
. C/ I! a& ?2 c. }2 U, l( ? │ │ ; v* N7 X! k7 x+ |, _
│ └─neuralnets-2012-001" q) q! O/ V) f) [" v6 U O
│ ├─01_Lecture1# M( e7 O/ x' E" B T
│ │ 01_Why_do_we_need_machine_learning_13_min.mp4
" _0 S' [2 b" U/ V2 [ [5 }6 s │ │ 01_Why_do_we_need_machine_learning_13_min.pdf# Y" `0 Q4 ^; ^% B6 w
│ │ 01_Why_do_we_need_machine_learning_13_min.pptx
2 E" B" C1 i! u0 ^5 j( Z4 `6 V+ J% ` │ │ 01_Why_do_we_need_machine_learning_13_min.srt4 _. T o1 n, u" y3 d, M
│ │ 01_Why_do_we_need_machine_learning_13_min.txt* E; Y8 P- O5 I$ t1 z q, V! Z$ k
│ │ 02_What_are_neural_networks_8_min.mp4: q- h. J- ?! H+ l7 F6 G8 K0 G: l
│ │ 02_What_are_neural_networks_8_min.srt8 \6 K$ h6 y# V, f3 K! g
│ │ 02_What_are_neural_networks_8_min.txt6 u/ M8 B/ \. T& G+ V' A9 } R# @
│ │ 03_Some_simple_models_of_neurons_8_min.mp4+ D$ X7 ~& N0 }" K
│ │ 03_Some_simple_models_of_neurons_8_min.srt
$ {* d& w3 \5 C, b │ │ 03_Some_simple_models_of_neurons_8_min.txt5 W+ E3 z9 l$ _8 ?
│ │ 04_A_simple_example_of_learning_6_min.mp44 X/ j! k, O. ]' a9 c+ W" O, ~
│ │ 04_A_simple_example_of_learning_6_min.srt, T C: E" D3 L$ \8 k
│ │ 04_A_simple_example_of_learning_6_min.txt
0 V. B. x3 f+ K │ │ 05_Three_types_of_learning_8_min.mp4
0 t: T: A2 j6 y0 H, K │ │ 05_Three_types_of_learning_8_min.srt
4 G/ ^: o. V5 x, g2 H8 p; V* \ │ │ 05_Three_types_of_learning_8_min.txt4 t6 N1 m) ]# T6 q, b( x. _
│ │ / Q. I& ?8 m" Y d9 E
│ ├─02_Lecture2" o+ w9 ?( k; V
│ │ 03_A_geometrical_view_of_perceptrons_6_min.mp44 W) V4 X/ a, `+ C8 X: ?, S
│ │ 03_A_geometrical_view_of_perceptrons_6_min.srt4 v0 X+ X7 x- g9 v, B
│ │ 03_A_geometrical_view_of_perceptrons_6_min.txt* U1 l5 x. ]7 J
│ │ 04_Why_the_learning_works_5_min.mp4
7 w; [( h( k9 N( d- v. n/ | │ │ 04_Why_the_learning_works_5_min.srt. ]' e2 O" P% e9 T* K' d5 `" O. F
│ │ 04_Why_the_learning_works_5_min.txt `6 E; E6 n9 r- o, T) y' e+ G: X" e
│ │ 05_What_perceptrons_cant_do_15_min.mp48 N$ h3 ~7 } Y: S; g% O$ ^9 Q4 c& R
│ │ 05_What_perceptrons_cant_do_15_min.srt2 {0 c+ J/ v1 s
│ │ 05_What_perceptrons_cant_do_15_min.txt
! D {; \5 B- u0 u │ │ n% \- z/ b" k6 n" b- i$ ?) d V+ P
│ ├─03_Lecture3
, y. U5 H8 a" C3 R4 j2 w* W │ │ 04_The_backpropagation_algorithm_12_min.mp4; `0 M) m+ S8 z' E. F
│ │ 04_The_backpropagation_algorithm_12_min.pdf9 ~# j. n! q$ B9 ~: G4 Q- ~: d
│ │ 04_The_backpropagation_algorithm_12_min.srt; B @" T& I' B
│ │ 04_The_backpropagation_algorithm_12_min.txt; ]4 U: p. n2 {; f1 I, Z5 J
│ │
$ A1 U2 m! V3 o: q" Y: W │ ├─04_Lecture4
; R' i r& {; u! \! B# q8 q │ │ 01_Learning_to_predict_the_next_word_13_min.mp4# O7 S1 Q; F+ \) l$ q/ u) N4 j- {4 G9 h
│ │ 01_Learning_to_predict_the_next_word_13_min.pdf
# {, {9 ~" M u │ │ 01_Learning_to_predict_the_next_word_13_min.pptx
^4 i+ \ e7 V6 l2 A( x │ │ 01_Learning_to_predict_the_next_word_13_min.srt
7 r9 D, g _! ~* C& w │ │ 01_Learning_to_predict_the_next_word_13_min.txt) Q, |9 g) T7 n& t
│ │ 04_Neuro-probabilistic_language_models_8_min.mp4 e y, P1 }1 q7 Y$ O* S. ]" Z- g
│ │ 04_Neuro-probabilistic_language_models_8_min.pdf) @) a3 ]+ E3 ^% [! q( I$ l
│ │ 04_Neuro-probabilistic_language_models_8_min.srt l& K8 u4 U) G% a
│ │ 04_Neuro-probabilistic_language_models_8_min.txt
2 t0 w c' K9 y9 a* i" V │ │
: ~, U0 O" L; |. J z- j3 |' P3 W" R7 x │ ├─05_Lecture5! v) O0 K+ v- I0 X$ t0 V1 R6 U
│ │ 01_Why_object_recognition_is_difficult_5_min.mp4# `( f. j' I1 @3 \0 w
│ │ 01_Why_object_recognition_is_difficult_5_min.pdf: V9 j; I8 `- K# q
│ │ 01_Why_object_recognition_is_difficult_5_min.srt1 |, N, p* g' b- Y: S
│ │ 01_Why_object_recognition_is_difficult_5_min.txt5 F* [) l! w# V; z* ?
│ │ 02_Achieving_viewpoint_invariance_6_min.mp4
1 b! m8 \. v/ Z5 i+ B" E- \' _$ Z │ │ 02_Achieving_viewpoint_invariance_6_min.srt
- I& z6 j8 L% r+ m6 W. y5 _ │ │ 02_Achieving_viewpoint_invariance_6_min.txt
- d$ G @8 |/ T │ │ , G# a& g8 m# r9 i
│ ├─06_Lecture6
1 |! T; Y) { K9 ? │ │ 01_Overview_of_mini-batch_gradient_descent.mp4
]. S& t, N) F0 C, }& o l │ │ 01_Overview_of_mini-batch_gradient_descent.pdf
2 C7 W5 M' u# q+ {/ i │ │ 01_Overview_of_mini-batch_gradient_descent.pptx! k5 u( x% W. h7 e1 S( w
│ │ 01_Overview_of_mini-batch_gradient_descent.srt k5 M8 w- S9 e% I4 n# V
│ │ 01_Overview_of_mini-batch_gradient_descent.txt5 n/ L8 j( }, \( [
│ │ 03_The_momentum_method.mp4
' _9 M% F+ F0 z4 ] │ │ 03_The_momentum_method.srt
3 W C! r: ~+ }9 g1 W5 d c │ │ 03_The_momentum_method.txt
" i% d3 @) T$ |' N! F' o │ │ 1 A, z* c; e7 X) w2 s4 F
│ ├─07_Lecture7) H Q% U5 J" n5 z' |
│ │ 01_Modeling_sequences-_A_brief_overview.mp4
$ `6 P8 i3 j2 ^& ?; N/ Y9 R │ │ 01_Modeling_sequences-_A_brief_overview.pdf
3 h7 y% l, ^3 \7 c% ^2 B │ │ 01_Modeling_sequences-_A_brief_overview.pptx" }0 k f6 B6 \8 t7 C
│ │ 01_Modeling_sequences-_A_brief_overview.srt
3 K# s* O S- @' J' _ │ │ 01_Modeling_sequences-_A_brief_overview.txt; @8 X0 ?6 q0 {% L& ~/ x
│ │ 02_Training_RNNs_with_back_propagation.mp4
8 d6 D7 u* }5 b& T6 l# `5 f6 x │ │ 02_Training_RNNs_with_back_propagation.srt
m5 T) Y5 r" ^9 N1 { │ │ 02_Training_RNNs_with_back_propagation.txt
* T1 _9 _# k& O9 U+ ]9 J5 O& z │ │ 03_A_toy_example_of_training_an_RNN.mp4
$ B# u4 z# X; A/ S3 U6 } │ │ 03_A_toy_example_of_training_an_RNN.srt* y( O5 `6 k+ Z
│ │ 03_A_toy_example_of_training_an_RNN.txt! M% c7 _1 J" `$ X: Q' G: j
│ │ 04_Why_it_is_difficult_to_train_an_RNN.mp4
p/ H, Z* R/ \/ I4 D; ` │ │ 04_Why_it_is_difficult_to_train_an_RNN.srt* z1 G% e N7 s4 H) r+ C+ T; B
│ │ 04_Why_it_is_difficult_to_train_an_RNN.txt
# c( U% |4 B- A- |9 t │ │ 05_Long-term_Short-term-memory.mp4
6 X+ _7 E. v% f1 U' i, a │ │ 05_Long-term_Short-term-memory.pdf
6 g: X) m2 J; [, d │ │ 05_Long-term_Short-term-memory.srt5 k8 J0 B7 ~3 E+ `! r
│ │ 05_Long-term_Short-term-memory.txt# o4 A& c# D7 O/ m$ k4 l
│ │
3 M( B) L: M$ H( y" s' H Q, Q7 ` │ ├─08_Lecture8' e4 J3 Z, R3 A+ q b Z
│ │ 04_Echo_State_Networks_9_min.mp4* q, e( p! L2 P$ l Q0 U. T3 [( v* y
│ │ 04_Echo_State_Networks_9_min.srt" x/ D7 `/ q* p1 T
│ │ 04_Echo_State_Networks_9_min.txt
" Q/ \3 y0 `' U8 { │ │ * f7 o. p# b8 ?3 m4 M1 N, K
│ ├─09_Lecture9
- D% |, g7 ?+ Z c │ │ 02_Limiting_the_size_of_the_weights_6_min.mp4
2 H" K& o8 K8 @# m6 V │ │ 02_Limiting_the_size_of_the_weights_6_min.srt
) W6 @2 Q! m6 I& C% @7 P% {& x; { │ │ 02_Limiting_the_size_of_the_weights_6_min.txt" z/ k( A/ p& ?7 L
│ │ 03_Using_noise_as_a_regularizer_7_min.mp4
; |8 F6 N$ s5 s ] │ │ 03_Using_noise_as_a_regularizer_7_min.srt6 K! Y1 N8 Z3 e& d
│ │ 03_Using_noise_as_a_regularizer_7_min.txt/ g! |* x) K) G
│ │
, i, b; [# [* l5 @& |* d9 z* } │ ├─10_Lecture10* _5 c8 O' x* Q
│ │ 01_Why_it_helps_to_combine_models_13_min.mp4
7 E( r K& l( j! \ H4 v │ │ 01_Why_it_helps_to_combine_models_13_min.pdf
5 \- W8 [& _! Z1 X' l* P │ │ 01_Why_it_helps_to_combine_models_13_min.pptx7 q9 h) m, W( ~4 A
│ │ 01_Why_it_helps_to_combine_models_13_min.srt7 r5 w& \. D( } h5 O) P' h5 F
│ │ 01_Why_it_helps_to_combine_models_13_min.txt* h. P2 u: y( n
│ │ 02_Mixtures_of_Experts_13_min.mp4% P' G) D6 d6 Q( ^4 m
│ │ 02_Mixtures_of_Experts_13_min.pdf
( E* ? G3 M2 p! x/ o │ │ 02_Mixtures_of_Experts_13_min.srt
5 s$ q" o5 }4 l& D4 y7 } │ │ 02_Mixtures_of_Experts_13_min.txt
; {2 _8 `5 I' P" w- v% x │ │ 03_The_idea_of_full_Bayesian_learning_7_min.mp43 ?+ U5 c/ M& N9 ? ~- W; j
│ │ 03_The_idea_of_full_Bayesian_learning_7_min.srt. a5 X! _8 `/ t! v: }) ?: K
│ │ 03_The_idea_of_full_Bayesian_learning_7_min.txt
& P0 a; H2 ]$ x( j( h) ^# {3 C │ │ 05_Dropout_9_min.mp4
- q4 P4 \5 ~7 u) |/ f$ L │ │ 05_Dropout_9_min.pdf
- }: [' B6 E& E! _9 s) @) e │ │ 05_Dropout_9_min.srt; |* o3 h h \! R+ ^# u% b, X
│ │ 05_Dropout_9_min.txt
& r7 e: H% {/ Y# i* n2 B1 c( K │ │ 2 D$ g) l9 o. [7 e; g/ R$ F
│ ├─11_Lecture11% y! G: t0 t3 |& `, v
│ │ 01_Hopfield_Nets_13_min.mp4
* E4 v( ?) I3 U │ │ 01_Hopfield_Nets_13_min.pdf
( j: u3 _$ j8 x e0 F │ │ 01_Hopfield_Nets_13_min.pptx
, Y! e4 l, L9 j │ │ 01_Hopfield_Nets_13_min.srt) ] ?4 t4 O# j
│ │ 01_Hopfield_Nets_13_min.txt
4 c9 S6 @# N9 B6 P4 d( Z5 L ] ^ │ │ 02_Dealing_with_spurious_minima_11_min.mp4 d( x% t8 ?: K7 A! G. ]9 E- n
│ │ 02_Dealing_with_spurious_minima_11_min.srt. z! i ]5 h5 j+ S
│ │ 02_Dealing_with_spurious_minima_11_min.txt0 T( \0 Y& q3 a! u- S# d+ ]* \
│ │ 03_Hopfield_nets_with_hidden_units_10_min.mp4
$ Q& |& x, ?3 q4 n/ z │ │ 03_Hopfield_nets_with_hidden_units_10_min.srt
5 m) s! t1 Y( B, y$ g3 K9 o4 ]% ? │ │ 03_Hopfield_nets_with_hidden_units_10_min.txt2 n1 w# {- S9 \ K# a; x5 V$ l2 {
│ │
0 R$ g' U" i/ B; U │ ├─12_Lecture12- m/ ~% ]8 _/ U; L$ W, c
│ │ 01_Boltzmann_machine_learning_12_min.mp4, |+ u) S E: m% A2 K$ a3 ?
│ │ 01_Boltzmann_machine_learning_12_min.pdf
( q1 B$ A4 x0 Y: `' N! m' h! }! I5 m5 j │ │ 01_Boltzmann_machine_learning_12_min.pptx" K: X. |) {* N4 B/ q
│ │ 01_Boltzmann_machine_learning_12_min.srt2 V. u5 O2 s/ [9 g2 ^6 |3 p
│ │ 01_Boltzmann_machine_learning_12_min.txt
5 G4 p# n0 b g0 R; ?' S' W │ │ 03_Restricted_Boltzmann_Machines_11_min.mp4: h8 { N1 m7 k
│ │ 03_Restricted_Boltzmann_Machines_11_min.srt, q3 ~5 u6 u3 c' ^: w% n3 N
│ │ 03_Restricted_Boltzmann_Machines_11_min.txt
4 N, U8 K# h; j' B │ │ 04_An_example_of_RBM_learning_7_mins.mp4
; n1 J5 X" n: z │ │ 04_An_example_of_RBM_learning_7_mins.srt4 ?( @9 ~& N7 B; x5 V2 `( c3 o
│ │ 04_An_example_of_RBM_learning_7_mins.txt
, ?0 Q8 K; K' X7 ^' O+ ?9 @ │ │ 05_RBMs_for_collaborative_filtering_8_mins.mp4& t0 D9 y% C: E8 f
│ │ 05_RBMs_for_collaborative_filtering_8_mins.srt
" B: `+ g. A5 M R& x2 U │ │ 05_RBMs_for_collaborative_filtering_8_mins.txt
# F, `' T/ m9 L7 n' U( s5 _ │ │ ( X/ P% o3 g5 X
│ ├─13_Lecture134 s/ l( T, p |. a* |
│ │ 02_Belief_Nets_13_min.mp4, N2 [" e& ?' ^, ~
│ │ 02_Belief_Nets_13_min.srt
2 q! b4 R% v9 z# D- c" h │ │ 02_Belief_Nets_13_min.txt
9 t& l2 w! F0 W9 @1 q │ │ 03_Learning_sigmoid_belief_nets_12_min.mp4% ^3 f5 U( S4 \) V ?; x; A
│ │ 03_Learning_sigmoid_belief_nets_12_min.pdf
1 {, m7 J4 @/ ~ ~' t │ │ 03_Learning_sigmoid_belief_nets_12_min.srt$ T. [+ m4 U8 \) J [- [
│ │ 03_Learning_sigmoid_belief_nets_12_min.txt
1 T& K5 i6 Y) g3 {/ T$ d │ │ 04_The_wake-sleep_algorithm_13_min.mp4
* f% C# N" @3 c; j, A$ ~ │ │ 04_The_wake-sleep_algorithm_13_min.pdf0 b9 d+ U# K0 _5 G$ J2 ^+ v* I9 J
│ │ 04_The_wake-sleep_algorithm_13_min.srt
/ y0 j# i1 v s1 G7 G5 A8 a │ │ 04_The_wake-sleep_algorithm_13_min.txt" x, v8 d. _* u
│ │ : X" y. i' f8 j J
│ ├─14_Lecture14: i7 [0 L2 b2 A, y% |. g
│ │ 02_Discriminative_learning_for_DBNs_9_mins.mp4+ ?3 f" [( {9 E$ Z3 x4 k) N
│ │ 02_Discriminative_learning_for_DBNs_9_mins.srt: y1 t2 I! L. F: ^3 V# Y+ V. w. a" Q6 ^
│ │ 02_Discriminative_learning_for_DBNs_9_mins.txt
9 a0 s7 c& u- ~! V │ │
* P* h! u! Y$ F, K/ z │ ├─15_Lecture15/ R9 R- V. h5 l5 \4 L, c- }; v
│ │ 01_From_PCA_to_autoencoders_5_mins.mp4
6 Q; O9 k: l/ m$ h' F; G. n │ │ 01_From_PCA_to_autoencoders_5_mins.pdf0 P. b( H" r0 m
│ │ 01_From_PCA_to_autoencoders_5_mins.pptx
$ L# M8 A3 O1 x( f9 z │ │ 01_From_PCA_to_autoencoders_5_mins.srt
& }; n! C) J% W- R2 h* _" g6 C. U │ │ 01_From_PCA_to_autoencoders_5_mins.txt
& n c G* w/ X+ g3 O │ │ 02_Deep_auto_encoders_4_mins.mp4
! f9 w' Z2 D0 I" C2 O │ │ 02_Deep_auto_encoders_4_mins.srt3 n4 {+ _3 B. C0 o: z9 E
│ │ 02_Deep_auto_encoders_4_mins.txt1 Q7 S1 V: q- p/ E" [( f
│ │ 04_Semantic_Hashing_9_mins.mp4# ?$ g* ], v2 @9 m
│ │ 04_Semantic_Hashing_9_mins.pdf5 M0 v- e! @) p% C! ? R* F: ^
│ │ 04_Semantic_Hashing_9_mins.srt6 n2 y( B* l' W8 P. P* y, F/ V. G) ]
│ │ 04_Semantic_Hashing_9_mins.txt/ j4 ^, u! U) Q0 U; X0 i* e6 F
│ │
0 n) p) B v- G0 p' H │ └─16_Lecture169 N; D' n- p- k4 @) b, g1 \4 |0 \
│ 04_OPTIONAL-_The_fog_of_progress_3_min.mp4
! ?; p3 \1 v) T( V" J0 T │ 04_OPTIONAL-_The_fog_of_progress_3_min.pdf# T7 s/ e' J( p; j+ m/ p
│ 04_OPTIONAL-_The_fog_of_progress_3_min.pptx5 f& v4 O6 [# e# l
│ 04_OPTIONAL-_The_fog_of_progress_3_min.srt
. H7 z3 l. _% k. U │ 04_OPTIONAL-_The_fog_of_progress_3_min.txt- W+ B. o. t* E6 E+ {% Z; d7 \
│ " u' i) M; a; q! o/ g
├─006_Probabilistic Graphical Models$ ?3 M) {. L: v0 U; r
│ └─006_Probabilistic Graphical Models
8 o9 H" s. V$ {5 N- a- b │ ├─pgm-003
% M8 ?5 z+ w7 p/ W1 m │ │ ├─01_Introduction_and_Overview- V- A L. \6 Q: b
│ │ │ 01_Welcome.mp4
! P$ D: N$ N$ C, @7 _+ W5 m+ p │ │ │ 01_Welcome.srt. e7 U9 Y$ g' H7 R5 n
│ │ │ 01_Welcome.txt
: h3 |! z; F, F+ D# T! F- t9 B, v │ │ │ 02_Overview_and_Motivation.mp4
8 v8 p* O. _1 S2 S% H │ │ │ 02_Overview_and_Motivation.srt& Z+ Y/ t2 w; F% ~
│ │ │ 02_Overview_and_Motivation.txt
$ C# S2 A4 \/ n! h6 P# F# z: d% X │ │ │ 03_Distributions.mp4
+ \2 F! I1 d1 x$ M$ p1 c/ n │ │ │ 03_Distributions.srt
# V$ q0 N1 `9 Q. _& E2 L/ u# f" l# \ │ │ │ 03_Distributions.txt! \5 t/ d; C3 s) K
│ │ │ 04_Factors.mp41 Q7 ]4 |/ E" R4 H
│ │ │ 04_Factors.srt
. ?9 \" X/ I! b8 A1 b3 X │ │ │ 04_Factors.txt
5 ]( R- {/ g9 M/ k5 J% W │ │ │
% i. k* s5 L+ }+ e │ │ ├─02_Bayesian_Network_Fundamentals+ {7 b( d" ^6 `! t- u0 w$ [
│ │ │ 01_Semantics_amp_Factorization.mp4
" O" T9 C5 ~- ]1 n │ │ │ 01_Semantics_amp_Factorization.srt- M8 k, u! X4 [
│ │ │ 01_Semantics_amp_Factorization.txt; Y0 L$ ~; A6 v+ L8 z
│ │ │ 02_Reasoning_Patterns.mp4' I7 f5 r8 ^ @( R0 R/ g) q
│ │ │ 02_Reasoning_Patterns.srt% ?& J `) B) U2 L
│ │ │ 02_Reasoning_Patterns.txt5 G, y! ?- j C8 p7 [! l
│ │ │ 03_Flow_of_Probabilistic_Influence.mp4
7 ^) u$ G- ]- d │ │ │ 03_Flow_of_Probabilistic_Influence.srt
6 r; A# g5 `( B; E │ │ │ 03_Flow_of_Probabilistic_Influence.txt% v) s7 y. a6 ^1 L0 G' q
│ │ │ 04_Conditional_Independence.mp4
) K5 P1 y7 F7 w │ │ │ 04_Conditional_Independence.srt
- L4 ?: \' l5 L7 D8 U3 a( o# ~ │ │ │ 04_Conditional_Independence.txt. F+ I$ q* z% B9 l; U6 c1 X0 x
│ │ │ 05_Independencies_in_Bayesian_Networks.mp4+ Y: \2 z- N0 z- \
│ │ │ 05_Independencies_in_Bayesian_Networks.srt# ^1 }8 r+ Y. X9 t
│ │ │ 05_Independencies_in_Bayesian_Networks.txt
' K2 @5 ]" x; ~+ @% B │ │ │ 06_Naive_Bayes.mp4" T9 {8 u- f8 c' w3 f7 p* A
│ │ │ 06_Naive_Bayes.srt5 a, E0 [' i+ m0 x7 L
│ │ │ 06_Naive_Bayes.txt
; s6 Z* I# ^) O9 V. V6 v │ │ │ 07_Application_-_Medical_Diagnosis.mp4
) M( X) m, ^3 b C9 a0 T │ │ │ 07_Application_-_Medical_Diagnosis.srt
: P& W) @7 M6 r3 T │ │ │ 07_Application_-_Medical_Diagnosis.txt2 t# s8 y+ [. m- e
│ │ │ 08_Knowledge_Engineering_Example_-_SAMIAM.mp4
W1 ?' X/ j. v8 u' D, b │ │ │ 08_Knowledge_Engineering_Example_-_SAMIAM.srt
2 n$ C% v$ o1 [/ h8 B5 o# e- Z* i │ │ │ 08_Knowledge_Engineering_Example_-_SAMIAM.txt
, c$ A# n" b6 d$ ^ │ │ │
2 t0 e- _2 y4 \# B& z/ Y │ │ ├─03_Template_Models, h, V3 a$ j* ?, c k
│ │ │ 01_Overview_of_Template_Models.mp4
) f+ n6 p/ }; _6 ~# l- w │ │ │ 01_Overview_of_Template_Models.srt8 g ~+ o5 d. s3 d5 U
│ │ │ 01_Overview_of_Template_Models.txt
6 }" t& ]: m6 h* h │ │ │ 02_Temporal_Models_-_DBNs.mp49 y/ ^9 a" Y9 C
│ │ │ 02_Temporal_Models_-_DBNs.srt( w& h. J. y. \, m4 s
│ │ │ 02_Temporal_Models_-_DBNs.txt
) D9 Z' ?; w7 l* Y+ t1 L │ │ │ 03_Temporal_Models_-_HMMs.mp4
- M, R, W8 t+ Z/ b- p# s9 n5 N │ │ │ 03_Temporal_Models_-_HMMs.srt E# K' f* r# ?$ ^. g
│ │ │ 03_Temporal_Models_-_HMMs.txt
* K: L7 R) ?& Y) R │ │ │ 04_Plate_Models.mp4, Z. b) `3 \* g( G
│ │ │ 04_Plate_Models.srt
" q5 }+ m6 Q/ n# S │ │ │ 04_Plate_Models.txt
# W: X; d" D f6 e │ │ │
- o( I$ y' G% i" o │ │ ├─04_ML-class_Octave_Tutorial
1 \) w1 c, o9 M) H% z S │ │ │ 01_Basic_Operations.mp4. b( t W' o X
│ │ │ 01_Basic_Operations.srt
+ s8 Y% c- c% P6 E │ │ │ 01_Basic_Operations.txt
3 J2 C& m0 G7 o }1 o │ │ │ 02_Moving_Data_Around.mp4) f/ t- Q7 H8 ]9 t; t
│ │ │ 02_Moving_Data_Around.srt
. e# v, k7 q9 S5 e │ │ │ 02_Moving_Data_Around.txt' g1 i$ s5 L# \" f c2 T
│ │ │ 03_Computing_On_Data.mp45 L/ k+ G$ u% h; S& |
│ │ │ 03_Computing_On_Data.srt
7 \( h$ N% T4 y* n │ │ │ 03_Computing_On_Data.txt
$ ?+ }7 Z }# H* H │ │ │ 04_Plotting_Data.mp4/ R$ q; e9 b! |2 U
│ │ │ 04_Plotting_Data.srt
% ?: s3 B4 Y% S/ k, d* ?- ], [ │ │ │ 04_Plotting_Data.txt# z- j0 {. S* d$ G& g2 V X4 Y: }
│ │ │ 05_Control_Statements-_for_while_if_statements.mp4
$ E1 y. T$ E* k │ │ │ 05_Control_Statements-_for_while_if_statements.srt: S: R, t' c! F# C3 K6 G: H% U
│ │ │ 05_Control_Statements-_for_while_if_statements.txt
" A: q. l& w7 G │ │ │ 06_Vectorization.mp45 }% \! l5 q* Z' a% K
│ │ │ 06_Vectorization.srt
4 l6 I0 \% M( U& \" z9 H │ │ │ 06_Vectorization.txt1 ]/ s* m# S% }0 b' \
│ │ │ 07_Working_on_and_Submitting_Programming_Exercises.mp4
. B4 M, {0 G% g8 D; X0 N3 w │ │ │ 07_Working_on_and_Submitting_Programming_Exercises.srt) Q# r- R& X+ ?* j1 E
│ │ │ 07_Working_on_and_Submitting_Programming_Exercises.txt
/ E- t. k8 f; ?+ j │ │ │
- B, ^. B9 A& B" O$ ] │ │ ├─05_Structured_CPDs* N+ s* t! U" j6 q
│ │ │ 01_Overview-_Structured_CPDs.mp4( C0 D' G9 x. o7 Y% {
│ │ │ 01_Overview-_Structured_CPDs.srt
- s6 b$ d" z8 c │ │ │ 01_Overview-_Structured_CPDs.txt
4 @- ~2 a* V6 u2 h8 A4 x │ │ │ 02_Tree-Structured_CPDs.mp46 i A9 c. ?8 m0 D* U
│ │ │ 02_Tree-Structured_CPDs.srt+ N- Z! v: v9 t8 H/ R% A) l
│ │ │ 02_Tree-Structured_CPDs.txt
. L8 m6 Z S5 |/ W │ │ │ 03_Independence_of_Causal_Influence.mp4/ [/ Y7 x/ f4 G
│ │ │ 03_Independence_of_Causal_Influence.srt) f' ~: n4 r2 b1 l/ y1 V: m
│ │ │ 03_Independence_of_Causal_Influence.txt! ~% c+ R/ B/ D7 Y) ]
│ │ │ 04_Continuous_Variables.mp4( q+ P [9 r- n$ ^% n6 J
│ │ │ 04_Continuous_Variables.srt3 I; M7 m- h1 {' _8 N
│ │ │ 04_Continuous_Variables.txt
3 N/ A* D8 S( Z5 | │ │ │ 7 X) f. `, k8 |$ J+ i
│ │ ├─06_Markov_Network_Fundamentals
* O& a0 }! R( |0 Z │ │ │ 01_Pairwise_Markov_Networks.mp4
4 F1 c* K$ B, M$ s. V │ │ │ 01_Pairwise_Markov_Networks.srt
& n; ~* N0 q/ u; M( L+ ^$ R* T │ │ │ 01_Pairwise_Markov_Networks.txt/ O" H$ e3 R# z8 ^
│ │ │ 02_General_Gibbs_Distribution.mp43 d7 m0 R9 `1 ]3 R
│ │ │ 02_General_Gibbs_Distribution.srt% c, A$ y$ t) F E# R
│ │ │ 02_General_Gibbs_Distribution.txt
0 `; s: P' M! A) U9 @; { │ │ │ 03_Conditional_Random_Fields.mp4
% _3 f- t( T4 B$ j2 o- _# ]. y │ │ │ 03_Conditional_Random_Fields.srt% E p4 Z1 `) n7 [) u s# l
│ │ │ 03_Conditional_Random_Fields.txt9 p/ I% l% S% X! l% l0 G) \
│ │ │ 04_Independencies_in_Markov_Networks.mp4
# s& g1 f7 t/ G7 s6 X+ h/ K │ │ │ 04_Independencies_in_Markov_Networks.srt
% a V4 h* s* Y" {$ z │ │ │ 04_Independencies_in_Markov_Networks.txt
# B2 S C2 L) u( C+ h │ │ │ 05_I-maps_and_perfect_maps.mp4: S" b+ X* N) i1 t9 Y- ] Q2 p
│ │ │ 05_I-maps_and_perfect_maps.srt- i$ T0 p1 ~+ g6 N
│ │ │ 05_I-maps_and_perfect_maps.txt$ o3 `" W+ A' s7 v/ B
│ │ │ 06_Log-Linear_Models.mp4
4 J+ V/ J n7 J+ Y& m# w) m │ │ │ 06_Log-Linear_Models.srt
* q' ^- b* x8 |( S1 L1 i/ I │ │ │ 06_Log-Linear_Models.txt
- V0 D4 b+ I! y6 y │ │ │ 07_Shared_Features_in_Log-Linear_Models.mp4
( x- Q. S5 K* G9 n* ? │ │ │ 07_Shared_Features_in_Log-Linear_Models.srt2 z+ t$ I3 b5 g5 u
│ │ │ 07_Shared_Features_in_Log-Linear_Models.txt4 v. e: I2 h. S2 m- G
│ │ │ : @" r3 d0 y U) W: F
│ │ ├─07_Representation_Wrapup-_Knowledge_Engineering
; o6 ^5 B5 S; u9 o4 P7 Z │ │ │ 01_Knowledge_Engineering.mp4
% G3 |$ q8 `/ e. @( c │ │ │ 01_Knowledge_Engineering.srt
) p& Y+ [" E' I │ │ │ 01_Knowledge_Engineering.txt
: Q" T- b: l, l- K" \0 n │ │ │ # p) Q7 Z5 t8 C8 U& {! A" i
│ │ ├─08_Inference-_Variable_Elimination
& u7 k% X' U# n, {: W& M; r │ │ │ 01_Overview-_Conditional_Probability_Queries.mp4; D5 @- G7 R; J
│ │ │ 01_Overview-_Conditional_Probability_Queries.srt
% W: L; r6 j6 E. V8 { │ │ │ 01_Overview-_Conditional_Probability_Queries.txt/ |. B8 Z7 A1 k4 j# D; M! k
│ │ │ 02_Overview-_MAP_Inference.mp4 G8 y [, u" g) n, W
│ │ │ 02_Overview-_MAP_Inference.srt
- o' }* P' [: ?1 E" ~- I3 b │ │ │ 02_Overview-_MAP_Inference.txt
( S6 I2 R+ c# i* {6 b, _ │ │ │ 03_Variable_Elimination_Algorithm.mp4& ^! ~' R+ n. `0 y; N% k; \0 u. ]
│ │ │ 03_Variable_Elimination_Algorithm.srt9 i' D& {7 m/ t. g/ ]9 d9 p
│ │ │ 03_Variable_Elimination_Algorithm.txt2 R1 K6 ~+ l* |$ O y
│ │ │ 04_Complexity_of_Variable_Elimination.mp48 b) C7 E Q" E ^9 D; l) j
│ │ │ 04_Complexity_of_Variable_Elimination.srt
; I( Z4 J0 {/ g e3 Z+ c. _ │ │ │ 04_Complexity_of_Variable_Elimination.txt
* p) x3 t% _2 }" k: O. v │ │ │ 06_Finding_Elimination_Orderings.mp4& n) D3 D5 q! S$ L# ]* |
│ │ │ 06_Finding_Elimination_Orderings.srt+ q2 q. e. V3 W! b- U; \
│ │ │ 06_Finding_Elimination_Orderings.txt q$ f) Q: j! [) b9 F
│ │ │
% M8 d; X% h* a Y' _" W │ │ ├─09_Inference-_Belief_Propagation_Part_1" I( i* ]4 N: h' S# K
│ │ │ 01_Belief_Propagation.mp4* S) G' m7 d0 A! a( X$ U% x
│ │ │ 01_Belief_Propagation.srt7 S5 j. s) ^! w8 s7 g+ o/ o
│ │ │ 01_Belief_Propagation.txt: \, N* \ f2 O2 ^# ^
│ │ │ 02_Properties_of_Cluster_Graphs.mp4
o6 \# j4 |, {; k │ │ │ 02_Properties_of_Cluster_Graphs.srt" M) E* a, k1 S0 Z- P: B
│ │ │ 02_Properties_of_Cluster_Graphs.txt$ w2 l& { `# K# r! r0 X- b
│ │ │
! ^8 L' ~9 n5 S0 K │ │ ├─10_Inference-_Belief_Propagation_Part_2
9 a) v1 |5 Q; L: O, c. H4 ?. V7 t! A' [3 l │ │ │ 01_Properties_of_Belief_Propagation.mp4
& r* I# X0 p. X( y5 `( b1 ? │ │ │ 01_Properties_of_Belief_Propagation.srt
: |" w; V9 J0 Q │ │ │ 01_Properties_of_Belief_Propagation.txt
f4 A# r2 n+ E& A │ │ │ 02_Clique_Tree_Algorithm_-_Correctness.mp4
' A) y# y1 }* Y+ v5 w8 h4 L( \. \ │ │ │ 02_Clique_Tree_Algorithm_-_Correctness.srt1 t7 q! N) w/ |1 G$ e: Z( g- J& h
│ │ │ 02_Clique_Tree_Algorithm_-_Correctness.txt
/ r$ Z7 m5 K# ^+ G3 x( \! t │ │ │ 03_Clique_Tree_Algorithm_-_Computation.mp4" C4 x4 _ I# u+ y
│ │ │ 03_Clique_Tree_Algorithm_-_Computation.srt
/ C1 B' [6 H+ C+ m5 z │ │ │ 03_Clique_Tree_Algorithm_-_Computation.txt
E5 g) D, L4 a3 G8 u3 ~. D) g5 h2 d6 w │ │ │ 04_Clique_Trees_and_Independence.mp4% c0 N) r3 \6 f5 D; X" a. w
│ │ │ 04_Clique_Trees_and_Independence.srt2 Q1 b" Z2 k% D
│ │ │ 04_Clique_Trees_and_Independence.txt
) X! n2 Y* l$ B6 |# a │ │ │ 05_Clique_Trees_and_VE.mp4
3 Y2 I0 l+ {8 `5 w │ │ │ 05_Clique_Trees_and_VE.srt
. F2 a8 S5 y( R* T6 z+ [# y4 p' K │ │ │ 05_Clique_Trees_and_VE.txt
/ W0 G/ n0 z) l' M. z: d8 ^ │ │ │ 06_BP_In_Practice.mp4
3 o# a0 }' X1 `- D. j3 h │ │ │ 06_BP_In_Practice.srt' Z: t7 P' c3 R2 l. F
│ │ │ 06_BP_In_Practice.txt
. K( E+ K+ U5 V9 E' p' X- o │ │ │ 07_Loopy_BP_and_Message_Decoding.mp4& a5 ] f* @# `
│ │ │ 07_Loopy_BP_and_Message_Decoding.srt, V7 T8 |- q( m' R5 i% |
│ │ │ 07_Loopy_BP_and_Message_Decoding.txt
5 M) u1 j$ y! L5 _6 z) V │ │ │
) k- e4 t- l2 A2 t) ?8 E/ |; p │ │ ├─11_Inference-_MAP_Estimation_Part_1
7 B' e; y( x/ z │ │ │ 01_Max_Sum_Message_Passing.mp4
! T2 m3 U7 e; x$ H │ │ │ 01_Max_Sum_Message_Passing.srt
) n/ L b4 b+ S1 y- q6 M- |# J │ │ │ 01_Max_Sum_Message_Passing.txt
6 E' u$ c& n7 s8 }5 L O' p9 C0 g8 m │ │ │ 02_Finding_a_MAP_Assignment.mp48 E: ]4 L/ n& {
│ │ │ 02_Finding_a_MAP_Assignment.srt
& L( x* R0 V- j! ?4 Q1 w8 l0 [ │ │ │ 02_Finding_a_MAP_Assignment.txt1 ^) R/ I( a* G2 L
│ │ │ + I4 P) E/ ?) j! {% _0 x
│ │ ├─12_Inference-_MAP_Estimation_Part_2
* @' e/ G: i3 N6 ~' r. e* Z │ │ │ 01_Tractable_MAP_Problems.mp43 u- V" W3 X8 p3 a
│ │ │ 01_Tractable_MAP_Problems.srt
J/ a+ t1 [9 V* s& r- W! X │ │ │ 01_Tractable_MAP_Problems.txt0 Y# c! j- [) T$ O- ~* M( t
│ │ │ 02_Dual_Decomposition_-_Intuition.mp4" n% V& g9 |5 B9 a3 @
│ │ │ 02_Dual_Decomposition_-_Intuition.srt% o, Q3 f4 j4 ~5 H( P
│ │ │ 02_Dual_Decomposition_-_Intuition.txt
! _5 F( Q- Y! F$ f │ │ │ 03_Dual_Decomposition_-_Algorithm.mp49 u! m( A7 \0 ~+ b: G
│ │ │ 03_Dual_Decomposition_-_Algorithm.srt
5 }; \% h w3 d" }0 y ^- g5 } │ │ │ 03_Dual_Decomposition_-_Algorithm.txt
! k. l- }) I+ r2 U │ │ │ ; P n3 y, D7 K l1 ]0 j
│ │ ├─13_Inference-_Sampling_Methods
9 `# o0 N$ b! U1 l* c │ │ │ 01_Simple_Sampling.mp4; ] G( T- j, ~9 a" S
│ │ │ 01_Simple_Sampling.srt
! j. c. Z' g2 I! Z: L5 @ │ │ │ 01_Simple_Sampling.txt
( p# ?% V8 E5 q- l( J# j │ │ │ 02_Markov_Chain_Monte_Carlo.mp4; N6 O$ t) Z4 F k- g# H
│ │ │ 02_Markov_Chain_Monte_Carlo.srt
6 }2 K5 B9 O4 }/ J6 k │ │ │ 02_Markov_Chain_Monte_Carlo.txt: ]& y* ?+ F8 X% ]7 X
│ │ │ 03_Using_a_Markov_Chain.mp4! v' d2 c! {+ U0 Z& x$ {
│ │ │ 03_Using_a_Markov_Chain.srt, y8 D. I2 {: @& N& Y
│ │ │ 03_Using_a_Markov_Chain.txt0 h8 e5 q5 R- w! v6 m
│ │ │ 04_Gibbs_Sampling.mp4
+ `& U) `6 ]4 x8 p) @# B" c │ │ │ 04_Gibbs_Sampling.srt/ H5 x; x* H6 [( Z- k3 P5 A
│ │ │ 04_Gibbs_Sampling.txt5 E4 U- s( L5 Q, d) ~/ q
│ │ │ 05_Metropolis_Hastings_Algorithm.mp4
$ l. N( V* E2 C0 r │ │ │ 05_Metropolis_Hastings_Algorithm.srt) }4 Q0 |! ]; `
│ │ │ 05_Metropolis_Hastings_Algorithm.txt1 |' [4 D6 {7 N8 a% F- S" y+ I
│ │ │
P) [, W: J: w0 u2 V0 v! Y* U/ m │ │ ├─14_Inference-_Temporal_Models_and_Wrap-up( b: m4 L! @ [8 W0 C) j/ M
│ │ │ 01_Inference_in_Temporal_Models.mp4
# k+ C3 B0 C/ n, I% \( D │ │ │ 01_Inference_in_Temporal_Models.srt
8 s/ t( u9 ~0 D# g+ c │ │ │ 01_Inference_in_Temporal_Models.txt0 Y% v( J# ?$ N
│ │ │ 02_Inference-_Summary.mp4
* T2 s Y8 L/ j# \% ]* d$ f% ^ │ │ │ 02_Inference-_Summary.srt* X& P9 t5 l. ^6 \9 U
│ │ │ 02_Inference-_Summary.txt
1 |) X! v. H4 w; J) z& u1 R" F │ │ │ 2 i9 h% ?+ |7 ~+ m
│ │ ├─15_Decision_Theory8 X" b. Q& O1 b' |% N) E& Y1 u
│ │ │ 01_Maximum_Expected_Utility.mp4
3 k' e9 i& v7 D' t: t+ Z │ │ │ 01_Maximum_Expected_Utility.srt
& T2 l4 _7 M2 _ u3 K4 }1 ? │ │ │ 01_Maximum_Expected_Utility.txt
0 ?3 u# u* N2 Y$ I- ^6 B' w4 _ │ │ │ 02_Utility_Functions.mp43 p& f7 L% Y( y4 {% M9 b4 W2 S
│ │ │ 02_Utility_Functions.srt
8 x8 p, X) t- |2 s) G1 h; c │ │ │ 02_Utility_Functions.txt
7 V6 s- N7 s: W: [5 y │ │ │ 03_Value_of_Perfect_Information.mp4 O. z/ w4 H: O5 Q
│ │ │ 03_Value_of_Perfect_Information.srt; u' D9 T, c! M
│ │ │ 03_Value_of_Perfect_Information.txt) o# p2 l2 z- v5 {% A' s4 `& {
│ │ │ # r7 x5 I# [; [3 S. v. z' t
│ │ ├─16_ML-class_Revision
9 P$ n% k5 p! X, \. f' _ │ │ │ 01_Regularization-_The_Problem_of_Overfitting.mp4' V. t9 a* }3 B5 M* @ W
│ │ │ 01_Regularization-_The_Problem_of_Overfitting.srt
; u$ X* J4 H" b: A, B2 Y │ │ │ 01_Regularization-_The_Problem_of_Overfitting.txt
0 i/ |" e# K) f2 n1 F │ │ │ 02_Regularization-_Cost_Function.mp4# P- u+ |3 C' a) O& b' Y
│ │ │ 02_Regularization-_Cost_Function.srt! H. C7 A; ?3 f4 Q1 N
│ │ │ 02_Regularization-_Cost_Function.txt9 q6 b6 e8 C3 G
│ │ │ 03_Evaluating_a_Hypothesis.mp4
5 |& t! s8 Y8 t* v. T! D( c │ │ │ 03_Evaluating_a_Hypothesis.srt" x+ e" V% D3 X G; c' C' ^
│ │ │ 03_Evaluating_a_Hypothesis.txt
/ {7 U7 d$ o) x3 W/ z( D* h │ │ │ 04_Model_Selection_and_Train_Validation_Test_Sets.mp41 {2 Z$ V+ a& g) y% s0 U l
│ │ │ 04_Model_Selection_and_Train_Validation_Test_Sets.srt
- E6 @2 l4 w8 r8 n, ` │ │ │ 04_Model_Selection_and_Train_Validation_Test_Sets.txt; f) P' k1 x4 \' E' ~( j) l. o
│ │ │ 05_Diagnosing_Bias_vs_Variance.mp4
: ^/ M, o7 X' w5 p+ K+ i │ │ │ 05_Diagnosing_Bias_vs_Variance.srt! \7 Y2 }4 M5 N# ?0 A
│ │ │ 05_Diagnosing_Bias_vs_Variance.txt
0 }4 M: |$ U1 z/ i) I7 W$ \, Z9 X* @ │ │ │ 06_Regularization_and_Bias_Variance.mp43 W p$ i3 N2 t+ y, ~) ~
│ │ │ 06_Regularization_and_Bias_Variance.srt9 @6 J% j7 o( a! q! C& I1 t, n; d
│ │ │ 06_Regularization_and_Bias_Variance.txt
$ g% u+ }- y/ i4 { R │ │ │ * e4 }" o0 y2 P0 W
│ │ ├─17_Learning-_Overview4 C+ I- ]5 o/ m
│ │ │ 01_Learning-_Overview.mp43 s |0 t* j7 N `0 k2 @8 f0 C: ^
│ │ │ 01_Learning-_Overview.srt
, [- \- b u. B# @- g │ │ │ 01_Learning-_Overview.txt
* t! R8 M7 v2 P' |& ` │ │ │ * S, C( n/ W" Y
│ │ ├─18_Learning-_Parameter_Estimation_in_BNs. j$ w# O' v( f7 s" F: [
│ │ │ 01_Maximum_Likelihood_Estimation.mp4% W* }: u" |0 w4 s: [
│ │ │ 01_Maximum_Likelihood_Estimation.srt/ g9 q9 K& b" ^8 B
│ │ │ 01_Maximum_Likelihood_Estimation.txt
! y1 X9 l. m" X: f) j1 j9 P+ l │ │ │ 03_Bayesian_Estimation.mp4! L1 ^: m0 A4 E& i
│ │ │ 03_Bayesian_Estimation.srt
# G4 l" Q! @5 a$ q3 C* U │ │ │ 03_Bayesian_Estimation.txt
/ I2 q5 D7 ]2 J) G/ x: r │ │ │ 04_Bayesian_Prediction.mp4
+ A- D, s; L" b2 C$ c4 l! G7 b │ │ │ 04_Bayesian_Prediction.srt
4 {7 H3 O. T5 c' b │ │ │ 04_Bayesian_Prediction.txt
v4 @8 ?1 t! ?4 c' h& y. w6 i │ │ │ 8 t* t% I! V/ T8 \% U+ K, H
│ │ ├─19_Learning-_Parameter_Estimation_in_MNs+ ]6 Z( ^: n: G" X7 O H
│ │ │ 03_MAP_Estimation_for_MRFs_and_CRFs.mp4 V+ e# S; B1 @+ I0 D% n$ ~( I
│ │ │ 03_MAP_Estimation_for_MRFs_and_CRFs.srt
$ `7 V6 d7 |% c% s0 n( x │ │ │ 03_MAP_Estimation_for_MRFs_and_CRFs.txt
% s& S. S) D6 x" E6 U2 v1 X2 ` │ │ │
9 t( K0 ?0 I0 ]) ^8 i │ │ ├─20_Structure_Learning$ u8 ~6 G& |3 M4 X' {) F
│ │ │ 01_Structure_Learning_Overview.mp4
9 Y+ }9 d; Z- _% j( {, O │ │ │ 01_Structure_Learning_Overview.srt
: r) R3 I8 _/ H" R0 j │ │ │ 01_Structure_Learning_Overview.txt
! y$ c! T, A) X9 w% C1 ` │ │ │ 02_Likelihood_Scores.mp4
! h/ e9 W# @' ?2 f: U; \' z" Z6 ` │ │ │ 02_Likelihood_Scores.srt
' p) z" T; Q7 K# m0 r X │ │ │ 02_Likelihood_Scores.txt
8 t' _: V& y# L8 E │ │ │ 03_BIC_and_Asymptotic_Consistency.mp48 n7 R! X) c1 z* Y9 Z9 N
│ │ │ 03_BIC_and_Asymptotic_Consistency.srt P$ p& w$ X: T
│ │ │ 03_BIC_and_Asymptotic_Consistency.txt
; O1 E3 Y( v+ S$ T- O T │ │ │ 04_Bayesian_Scores.mp4. W4 h9 f+ O+ X$ l$ O9 U! U5 w
│ │ │ 04_Bayesian_Scores.srt0 g/ f$ v! ^5 g( U: c, N# ]
│ │ │ 04_Bayesian_Scores.txt
& Z5 c9 C; ~2 n/ @( p │ │ │ 05_Learning_Tree_Structured_Networks.mp4
* |# G. m! g( d L3 ?, s) g' H │ │ │ 05_Learning_Tree_Structured_Networks.srt
# H# Y, a3 D: Q+ |: \3 v4 F( Q* D$ w │ │ │ 05_Learning_Tree_Structured_Networks.txt' ?/ y" f) `) E% N1 x
│ │ │ 06_Learning_General_Graphs-_Heuristic_Search.mp4) h6 k2 @: i9 I" U7 p5 d m
│ │ │ 06_Learning_General_Graphs-_Heuristic_Search.srt
9 F& t3 A& y: U% f2 u, d) \4 v │ │ │ 06_Learning_General_Graphs-_Heuristic_Search.txt" [4 |8 h* j& o2 E6 e; K1 n
│ │ │ 07_Learning_General_Graphs-_Search_and_Decomposability.mp4& A8 J. K0 Z; ^
│ │ │ 07_Learning_General_Graphs-_Search_and_Decomposability.srt
. ^- S: Q# X& C# `& o5 P3 ~3 k* R │ │ │ 07_Learning_General_Graphs-_Search_and_Decomposability.txt! T# E& ]6 m( e3 z& U
│ │ │ V, v. Q' Q& `- B( g
│ │ ├─21_Learning_With_Incomplete_Data8 ~* ~; q3 { @9 {
│ │ │ 01_Learning_With_Incomplete_Data_-_Overview.mp44 u N0 `+ I4 f* B
│ │ │ 01_Learning_With_Incomplete_Data_-_Overview.srt7 O2 q1 ]- R; e& z+ @
│ │ │ 01_Learning_With_Incomplete_Data_-_Overview.txt
8 @* r. u; y/ p! _% T( P3 j │ │ │ 02_Expectation_Maximization_-_Intro.mp4+ s2 i- C) x# ?$ b* {
│ │ │ 02_Expectation_Maximization_-_Intro.srt6 h# B3 @' R+ `5 C6 z
│ │ │ 02_Expectation_Maximization_-_Intro.txt: }1 v9 i3 T9 {/ V+ r( }
│ │ │ 03_Analysis_of_EM_Algorithm.mp44 H* @% c3 |8 {+ Y" Z- f& f% V5 v! D
│ │ │ 03_Analysis_of_EM_Algorithm.srt
* M5 B; g$ @" ^! Q J5 \: \' f3 W# J │ │ │ 03_Analysis_of_EM_Algorithm.txt
6 o' D& Z* p* F │ │ │ 04_EM_in_Practice.mp4
7 H9 @# Z8 U1 Q& I4 M: ~: T$ Q │ │ │ 04_EM_in_Practice.srt
0 F6 u% Z" U% F: @ │ │ │ 04_EM_in_Practice.txt
6 H& r1 D3 z: q │ │ │ 05_Latent_Variables.mp43 l$ k* F/ m# v {
│ │ │ 05_Latent_Variables.srt
$ Z3 x7 w+ i% X( E4 O( s3 @ │ │ │ 05_Latent_Variables.txt8 u. n8 U7 g1 ~- g/ P
│ │ │ % t7 w8 K' b. u: L( `9 p8 f0 `
│ │ ├─22_Learning-_Wrapup
" S$ B( O2 h# }' S │ │ │ 01_Summary-_Learning.mp4
) `2 R, x% c) _ │ │ │ 01_Summary-_Learning.srt
; y! m6 Q% G# n1 \6 _) s$ G │ │ │ 01_Summary-_Learning.txt
/ `3 m8 P5 o3 j2 J _ │ │ │
* F6 _' x8 C8 t; _7 s" F │ │ └─23_Summary
s7 b. k9 r! x2 x4 J7 i, m │ │ 01_Class_Summary.mp43 _, }8 `/ R% U6 O3 c" |7 O1 a
│ │ 01_Class_Summary.srt7 F, k# u1 a8 G9 p0 e5 U+ ]7 j$ y
│ │ 01_Class_Summary.txt5 w' U0 Y9 v& A8 w6 D) |
│ │
: a" Y. }. ]) z- i3 i9 G0 F │ └─Probabilistic Graphical Models - Stanford
' u2 J$ x; ]' {! ]* e& O │ 1 - 1 - Welcome! (05-35).mp4
) m0 |/ V" z' D" V+ R/ G& ?, K │ 1 - 1 - Welcome! (05-35).srt! b5 B0 Q& ~8 A' h3 H) t
│ 1 - 2 - Overview and Motivation (19-17).mp4
- K1 |( { G, ^- M% |" p │ 1 - 2 - Overview and Motivation (19-17).srt, f& S8 P: j. M: t! R4 r1 m5 G) ?: i. R
│ 1 - 3 - Distributions (04-56).mp49 }8 `( P/ C n9 Z
│ 1 - 3 - Distributions (04-56).srt# M: P, V2 c! f2 N! d
│ 1 - 4 - Factors (06-40).mp4 M1 t& Z. [( }7 ]1 }
│ 1 - 4 - Factors (06-40).srt
" p# H: a" n: o! T: l0 ~ N │ 10 - 4 - Clique Trees and Independence (15-21).mp4
0 p- Z9 n0 c9 j* f3 z1 _. d e │ 10 - 4 - Clique Trees and Independence (15-21).srt1 s8 D6 f+ o. ^& G; G
│ 10 - 5 - Clique Trees and VE (16-17).mp4! n# o7 x" z- V: r* P
│ 10 - 5 - Clique Trees and VE (16-17).srt
5 q1 g/ z' y5 x8 z* y" @; h │ 10 - 6 - BP In Practice (15-38).mp4
( q! X4 W6 Q/ g; d$ v │ 10 - 6 - BP In Practice (15-38).srt6 S+ {- c* v2 G- w/ O& j
│ 10 - 7 - Loopy BP and Message Decoding (21-42).mp45 ^, q! J: D: e N N B7 G$ N
│ 10 - 7 - Loopy BP and Message Decoding (21-42).srt a0 }2 N& z5 }" n& D9 V
│ 11 - 1 - Max Sum Message Passing (20-27).mp4
' S, |0 B4 y0 o& t/ h( x │ 11 - 1 - Max Sum Message Passing (20-27).srt
8 d# h# |& `7 A+ L5 @& o2 @ │ 11 - 2 - Finding a MAP Assignment (3-57).mp4: a8 Y8 k& O1 V7 M
│ 11 - 2 - Finding a MAP Assignment (3-57).srt( T9 @: Z% z3 \6 D. f
│ 12 - 1 - Tractable MAP Problems (15-04).mp4
) G9 C" i4 H% ?& p4 c │ 12 - 1 - Tractable MAP Problems (15-04).srt1 h* W8 K; z: {# C; I
│ 13 - 1 - Simple Sampling (23-37).mp4, N1 {: @9 @5 c6 L+ k
│ 13 - 1 - Simple Sampling (23-37).srt' M' E6 P; ^3 T9 G9 |, j
│ 13 - 2 - Markov Chain Monte Carlo (14-18).mp4" }- l6 g8 P1 c2 a9 i
│ 13 - 2 - Markov Chain Monte Carlo (14-18).srt. W0 N# H; G: s
│ 13 - 3 - Using a Markov Chain (15-27).mp4* m6 K! x( ]( t3 I
│ 13 - 3 - Using a Markov Chain (15-27).srt: {- [3 V5 m# t1 r Z
│ 13 - 4 - Gibbs Sampling (19-26).mp4
V4 V3 y- {, n$ w" ` a4 i │ 13 - 4 - Gibbs Sampling (19-26).srt: v( t) d8 F+ v+ H+ Q- L# O `
│ 13 - 5 - Metropolis Hastings Algorithm (27-06).mp43 {( y% n; Z7 U8 \: T" K& H
│ 13 - 5 - Metropolis Hastings Algorithm (27-06).srt; S$ f/ W m$ G* A$ x4 k+ J+ K
│ 14 - 1 - Inference in Temporal Models (19-43).mp49 |3 O! X3 _8 u( `1 V7 D
│ 14 - 1 - Inference in Temporal Models (19-43).srt7 j) d, S6 ~+ z# c
│ 14 - 2 - Inference- Summary (12-45).mp4/ i8 w3 q- C, q T
│ 14 - 2 - Inference- Summary (12-45).srt4 Y( ]8 {6 M& q, l
│ 15 - 1 - Maximum Expected Utility (25-57).mp4 Z" u. a# W1 v2 n
│ 15 - 1 - Maximum Expected Utility (25-57).srt) K: D1 l# ^7 K7 o' J* @
│ 15 - 2 - Utility Functions (18-15).mp4# q+ G9 O9 Z/ @* I9 P
│ 15 - 2 - Utility Functions (18-15).srt# j f) j: V% k; F
│ 15 - 3 - Value of Perfect Information (17-14).mp4
' G: e* D/ k- \" P! ` │ 15 - 3 - Value of Perfect Information (17-14).srt. l8 d+ d' Q0 r0 s* D( _! I/ Q
│ 16 - 2 - Regularization- Cost Function (10-10).mp4$ S' w, [# X, M7 H9 P L
│ 16 - 2 - Regularization- Cost Function (10-10).srt
6 g! T2 B3 H8 Q+ a( U0 ^ │ 16 - 3 - Evaluating a Hypothesis (07-35).mp4
: r6 C8 `1 N& r+ N │ 16 - 3 - Evaluating a Hypothesis (07-35).srt
9 _. Q5 w$ L3 p; ` │ 16 - 5 - Diagnosing Bias vs Variance (07-42).mp4; Q9 f) K( A& _
│ 16 - 5 - Diagnosing Bias vs Variance (07-42).srt
& ~9 x( _1 [9 g6 k │ 17 - 1 - Learning- Overview (15-35).mp4
$ M) e& j3 c. e& { │ 17 - 1 - Learning- Overview (15-35).srt
" l- Q: S8 a' O( { │ 18 - 1 - Maximum Likelihood Estimation (14-59).mp46 v+ ~. b/ t; b, V1 e
│ 18 - 1 - Maximum Likelihood Estimation (14-59).srt
6 y' S @; f Q1 f9 k. S │ 18 - 3 - Bayesian Estimation (15-27).mp4
& `9 f. h( v0 B" C" G │ 18 - 3 - Bayesian Estimation (15-27).srt) P! e( e: @5 e1 a
│ 18 - 4 - Bayesian Prediction (13-40).mp4& Y3 U+ Y3 c( }1 v) n/ s0 `: [' z
│ 18 - 4 - Bayesian Prediction (13-40).srt! Z( g8 \2 s$ i- d0 M; o
│ 2 - 1 - Semantics & Factorization (17-20).mp4
U# t# ?* }% B. P; y │ 2 - 1 - Semantics & Factorization (17-20).srt& I* L& m, ? V6 t \" U
│ 2 - 2 - Reasoning Patterns (09-59).mp4
, C+ q* f# m4 k' _ t8 ? │ 2 - 2 - Reasoning Patterns (09-59).srt J7 ]7 v ?; ?; m5 o Q
│ 2 - 4 - Conditional Independence (12-38).mp4$ F6 j; E, I# \4 a
│ 2 - 4 - Conditional Independence (12-38).srt) e& H$ S1 M* T+ q- a! ]" T
│ 2 - 6 - Naive Bayes (09-52).mp4
8 Y3 Z8 e5 C+ B- L9 Y4 e │ 2 - 6 - Naive Bayes (09-52).srt" }0 T( L& B# U/ t* W. R' P
│ 20 - 1 - Structure Learning Overview (5-49).mp4
: ?; x" }% m' y& Z9 g$ x; m │ 20 - 1 - Structure Learning Overview (5-49).srt
! f8 C4 r% K) _) W6 l │ 20 - 2 - Likelihood Scores (16-49).mp4
) j) f# o5 P& U │ 20 - 2 - Likelihood Scores (16-49).srt$ y, m& Q! D& J$ j' b" z
│ 20 - 4 - Bayesian Scores (20-35).mp4$ u' g, {) z" I7 ]' `! a& q
│ 20 - 4 - Bayesian Scores (20-35).srt
5 \8 }8 G, A# ~$ }3 C5 D' `) i │ 21 - 3 - Analysis of EM Algorithm (11-32).mp4
- ?. j# M5 D( h. D │ 21 - 3 - Analysis of EM Algorithm (11-32).srt
2 c# } q. b6 \0 T7 V7 a% ` │ 21 - 4 - EM in Practice (11-17).mp4
$ P' R3 Z6 \, b6 e0 w3 r& N8 I7 n │ 21 - 4 - EM in Practice (11-17).srt
" d0 ^6 [' Q; `, a# m5 c │ 21 - 5 - Latent Variables (22-00).mp4 K$ h8 r( K/ j4 o% \! P
│ 21 - 5 - Latent Variables (22-00).srt
K% c6 Y. Z2 E6 R2 ~ │ 22 - 1 - Summary- Learning (20-11).mp43 U, G* f/ b$ n7 d2 n; m6 G
│ 22 - 1 - Summary- Learning (20-11).srt
6 u$ V8 N. B) X. f5 G7 I' B │ 23 - 1 - Class Summary (24-38).mp4( ]5 l- K4 w; c) Q
│ 23 - 1 - Class Summary (24-38).srt' }0 r2 u% z; L9 K s7 N' J" J0 i! d
│ 3 - 1 - Overview of Template Models (10-55).mp4' u6 N% n/ F- X8 F' O
│ 3 - 1 - Overview of Template Models (10-55).srt: v9 j Z) [8 t( s
│ 3 - 2 - Temporal Models - DBNs (23-02).mp4
9 o, O! J3 P4 ?. T5 k6 z' Y/ C9 ~ │ 3 - 2 - Temporal Models - DBNs (23-02).srt/ O; k' Q6 U: A. o: m
│ 3 - 3 - Temporal Models - HMMs (12-01).mp4
6 B- p- t( d. s' i) O1 K │ 3 - 3 - Temporal Models - HMMs (12-01).srt4 C# N% `$ [5 X& k+ ?
│ 3 - 4 - Plate Models (20-08).mp4
. w. B$ ?- y: Z4 L2 I │ 3 - 4 - Plate Models (20-08).srt: A) C$ L1 e. ^1 U+ N' N" i
│ 4 - 1 - Basic Operations (13-59).mp4
- ^! ] a x7 E' | │ 4 - 1 - Basic Operations (13-59).srt
$ G& B4 n' G# _7 d │ 4 - 2 - Moving Data Around (16-07).mp4! v6 c% ~. e/ ^, l: [
│ 4 - 2 - Moving Data Around (16-07).srt0 G) f' N7 M ~, B" e u
│ 4 - 3 - Computing On Data (13-15).mp45 L) l6 k) u6 c$ t B
│ 4 - 3 - Computing On Data (13-15).srt+ ~0 J7 }& d+ ~4 e
│ 4 - 4 - Plotting Data (09-38).mp4
! m5 q0 Z2 g6 H/ T- ]) x$ ^ ` │ 4 - 4 - Plotting Data (09-38).srt/ y7 M' I, }1 l. Q) t6 J
│ 4 - 6 - Vectorization (13-48).mp4) Q& L4 @0 x/ S% q# w- k: R
│ 4 - 6 - Vectorization (13-48).srt8 _+ N* g3 W1 P$ `8 W
│ 5 - 1 - Overview- Structured CPDs (08-00).mp49 v" \' v) W5 o3 Y d1 C4 e
│ 5 - 1 - Overview- Structured CPDs (08-00).srt9 v" O; m0 u5 x$ p
│ 5 - 2 - Tree-Structured CPDs (14-37).mp4
/ O1 h* p+ F N+ M1 K: b& A1 t │ 5 - 2 - Tree-Structured CPDs (14-37).srt
2 U& i: a, Z' I2 S; I1 z │ 5 - 4 - Continuous Variables (13-25).mp4
5 B" _0 Q5 B9 \! i6 J! H# U* W │ 5 - 4 - Continuous Variables (13-25).srt
! A* R2 ]- {/ A1 Y │ 6 - 1 - Pairwise Markov Networks (10-59).mp4
. d2 q# ~4 k7 x2 Y7 C/ j8 b1 x │ 6 - 1 - Pairwise Markov Networks (10-59).srt
1 C7 M+ S/ t# R6 ?5 i" V0 p1 m- d │ 6 - 2 - General Gibbs Distribution (15-52).mp4
! k$ `! N/ e2 }! u% } │ 6 - 2 - General Gibbs Distribution (15-52).srt
; @' @( m$ @* ~ e6 v& H │ 6 - 3 - Conditional Random Fields (22-22).mp49 n: g" p5 ^/ ^1 i. r% Y
│ 6 - 3 - Conditional Random Fields (22-22).srt% e4 V4 ?, t8 V4 D& V6 @
│ 6 - 5 - I-maps and perfect maps (20-59).mp4
" L s6 C2 V( F0 p: m │ 6 - 5 - I-maps and perfect maps (20-59).srt
& w+ H0 Y2 S }4 B% e9 N+ _ │ 6 - 6 - Log-Linear Models (22-08).mp4( ~8 w( z7 J, h3 ~6 e5 a
│ 6 - 6 - Log-Linear Models (22-08).srt
9 S4 v* M! w! r& a │ 7 - 1 - Knowledge Engineering (23-05).mp46 D8 l" n+ a( ]) V, m7 ]
│ 7 - 1 - Knowledge Engineering (23-05).srt
$ w. b @$ r& I$ Y) G. l, i% R) ~4 k │ 8 - 2 - Overview- MAP Inference (09-42).mp40 d$ \; w$ I+ c; _; Q+ z4 G3 P
│ 8 - 2 - Overview- MAP Inference (09-42).srt
! g6 C. x, d$ Y │ 8 - 3 - Variable Elimination Algorithm (16-17).mp4) g: K1 v% h6 q) y' V
│ 8 - 3 - Variable Elimination Algorithm (16-17).srt
6 Q0 w7 T3 N3 [- y6 G1 a8 _ │ 8 - 6 - Finding Elimination Orderings (11-58).mp4; k3 k! W% W5 t; w3 f+ x- ~
│ 8 - 6 - Finding Elimination Orderings (11-58).srt
2 ~/ E$ \% N7 K. k! w. I │ 9 - 1 - Belief Propagation (21-21).mp4% n8 r- o9 @( q% }
│ 9 - 1 - Belief Propagation (21-21).srt
0 F; F) s7 Y I9 ], u( J │ 9 - 2 - Properties of Cluster Graphs (15-00).mp4- x! a2 t2 ~6 x' w, s
│ 9 - 2 - Properties of Cluster Graphs (15-00).srt
6 ]; q. H& q$ ]* Q2 r9 W* Y6 ` │ PGM-Programming_Assignment_1.zip
% v) g- C& N# X │ PGM-Programming_Assignment_2.zip: C. v% R D* _. z, j4 A5 i. j
│ PGM-Programming_Assignment_3.zip
$ p' { U2 M6 @4 Y- [6 F1 ]" d1 c │ PGM-Programming_Assignment_4.zip
4 z R4 k/ {# p/ m# u- m/ c- d │ PGM-Programming_Assignment_5.zip
7 S! V7 N% v e; |) X │ PGM-Programming_Assignment_6.zip
- Z2 f- P- b9 p* U' P │ PGM-Programming_Assignment_7.zip
# ?9 C: t# S* @6 E+ m: T │ PGM-Programming_Assignment_8.zip
2 D; D; s5 P2 u$ o │ PGM-Programming_Assignment_9.zip
. @8 H) @/ F1 u │ 下载说明.txt
$ @! G( s3 H& L9 O │ 关注我们.png
& ~3 x1 }$ d7 ~+ i1 T │ 攻城狮论坛=网络技术+编程视频.url& M- o6 A5 G% ]/ U& k
│ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt
3 [+ T% T7 I0 z0 j% V2 m │
7 \5 H. H; c5 y4 H c ├─031_台大概率; }) l1 \3 \% J3 F2 }
│ └─031_台大概率0 `8 |( \9 ~" Z1 M
│ ├─prob-0012 M# |7 Q J6 A0 N( O3 z
│ │ ├─01_Week_16 a; b4 c& E& W3 q5 F$ C( O
│ │ │ 01_1-0.mp4
( p" Q' |/ B! R# ]9 ~$ ~" m │ │ │ 02_1-1_17-41.mp40 ^( X8 j a- I/ N
│ │ │ 02_1-1_17-41.pdf$ u" z9 {4 m. m8 B
│ │ │ 02_1-1_17-41_0_.pdf$ g5 X2 j6 r- S2 q0 }/ b+ q b
│ │ │ 02_1-1_17-41_1_.pdf+ _0 X. T) [" l& I) G( ^7 Z- e& x
│ │ │ 02_1-1_17-41_2_.pdf" Z6 z/ S0 g3 Q, j* Q/ j: R
│ │ │ 03_1-2.a__11-46.mp4
3 X* H& H% i/ Z │ │ │ 04_1-2.b__09-40.mp4# S0 J0 ?3 M7 U# j2 f3 S- i; e6 I3 q
│ │ │ 05_1-3.a__11-24.mp4 G' _9 k; x9 Y+ i$ l$ t& `
│ │ │ 06_1-3.b__16-36.mp4
# b: P1 P! O7 o3 O/ Y4 l/ O │ │ │ . g3 m" z3 a1 L/ T9 [- H/ ~/ d
│ │ ├─02_Week_20 H: V: ]' u! s+ O4 r
│ │ │ 01_2-0_15-32.mp40 D" M& V! P- P2 I0 y' C
│ │ │ 02_2-1.a__16-09.mp45 m: `* ~; H+ X+ F* m: M8 S# P+ j7 o
│ │ │ 02_2-1.a__16-09.pdf
H* X2 f! k' J" b6 r: u& G, H │ │ │ 02_2-1.a__16-09_0_.pdf: d& H; \7 [7 e f/ H1 w0 w; D5 Y! @
│ │ │ 02_2-1.a__16-09_1_.pdf/ [3 t1 [( g( \, C4 d$ a
│ │ │ 02_2-1.a__16-09_2_.pdf
( L& V( h- T& O0 p │ │ │ 03_2-1.b__16-06.mp4
8 ~- {- S2 w: l7 Q$ U │ │ │ 04_2-1.c__10-07.mp4( i; b" T2 ~# ~' r; D' |, s9 X- {
│ │ │ 05_2-2.a__10-41.mp4
: g7 F4 b) `1 Q/ ~" E# w │ │ │ 06_2-2.b__12-43.mp4
% k9 m' j; ?4 ^- c& [, F │ │ │ 07_2-2.c__16-02.mp4
5 v4 q2 c: R5 r: J$ e4 `8 ^ │ │ │ $ `( F& b$ V3 y2 q$ B
│ │ ├─03_Week_3
- W0 `* y) I5 S8 f* I/ C │ │ │ 01_3-0_16-46.mp4) N n* A7 h( e) i
│ │ │ 02_3-1.a___09-12.mp4
; ?, P* a! n, G; u2 G0 y2 I6 Y │ │ │ 02_3-1.a___09-12.pdf4 B* d& m: T: w! K+ ^; ^
│ │ │ 02_3-1.a___09-12_0_.pdf
- C, Y; l% P A+ I' i# M- n# i% W │ │ │ 02_3-1.a___09-12_1_.pdf
& p4 s8 r' p" l0 ~0 F# _9 T │ │ │ 02_3-1.a___09-12_2_.pdf2 W, l6 [ q' H A; q8 w# @4 o
│ │ │ 03_3-1.b__10-35.mp40 @ v) h& k! C* T) o! i$ Q5 N
│ │ │ 04_3-2_08-47.mp4/ ?$ ]" T$ G8 T( x
│ │ │ 05_3-3.a__16-57.mp40 p* x8 }0 e4 j0 N
│ │ │ 06_3-3.b__12-58.mp40 Q- j# {4 b9 a% z
│ │ │
3 |; k1 e+ P# r" V' V4 M │ │ ├─04_Week_4
6 @0 z2 e! q! j9 w; H4 ~1 l │ │ │ 01_4-0_17-33.mp4: \+ R; v& W2 N1 l: S7 T7 {
│ │ │ 02_4-1.a__13-53.mp4$ e" J: b0 e- o& ^- b
│ │ │ 02_4-1.a__13-53.pdf/ f! V3 \4 {& ~4 L8 E
│ │ │ 02_4-1.a__13-53_0_.pdf
5 f; c0 l8 R# ` │ │ │ 02_4-1.a__13-53_1_.pdf
5 M" H; z+ V+ d' d3 |+ i ` │ │ │ 02_4-1.a__13-53_2_.pdf1 k5 F" \3 c$ x% n! U6 T3 s% B
│ │ │ 03_4-1.b__14-43.mp4. U! x- ~. N( t
│ │ │ 04_4-1.c__5-18.mp41 Z2 Q6 L+ O% k5 ~: B- U
│ │ │ 05_4-2.a_CDF__9-48.mp45 ^! P4 G) p! G' Y+ A# I
│ │ │ 06_4-2.b_CDF__8-59.mp4
& F- g5 Y/ N" \2 l: n │ │ │ 07_4-2.c_CDF__9-00.mp4
# B6 Y& ?: O& t$ ?) B4 ]: @* w! p │ │ │ 08_4-3_PMF_11-26.mp42 h/ X! e4 r* Q2 f- ^
│ │ │ 09_4-4.a_I__14-41.mp4! W! k' C1 {( {5 K3 O- B3 c
│ │ │ 10_4-4.b_I__8-47.mp4" z0 d$ T, b5 N4 v! }) @
│ │ │ . U) j& P5 Y) p! U4 p2 k
│ │ ├─05_Week_5& A9 g; `. {7 o$ u# C
│ │ │ 01_5-0_14-09.mp4- w7 w6 h6 Q6 w; M" w3 ~( ~
│ │ │ 02_5-1.a_II__10-36.mp41 t% y" S0 f, c3 c% G: e% C1 F. m
│ │ │ 02_5-1.a_II__10-36.pdf
8 R2 Q4 J( c" y6 ~ │ │ │ 02_5-1.a_II__10-36_0_.pdf
- i% B3 u9 g9 V) Z& d │ │ │ 02_5-1.a_II__10-36_1_.pdf3 r4 a, f3 [4 D1 C+ {# X
│ │ │ 02_5-1.a_II__10-36_2_.pdf
7 t* a3 N. |! X0 A) o' E │ │ │ 03_5-1.b_II__12-06.mp4) g2 G+ d1 q: g
│ │ │ 04_5-1.c_II__20-28.mp4% t9 p: s8 x- S
│ │ │ 05_5-2_PDF_18-56.mp4% @+ o C% E: g
│ │ │ 06_5-3_I_18-12.mp4
/ c. V6 v4 H( U9 q1 W* E │ │ │ o& J" Y! ?; j
│ │ ├─06_Week_6/ Y: [$ s9 e6 ` m9 t# N
│ │ │ 01_6-0_10-13.mp4
% M7 h6 h2 O# u5 X* A. t/ a │ │ │ 02_6-1.a_II__15-25.mp4
& v1 P3 D( P) I1 H, y │ │ │ 02_6-1.a_II__15-25.pdf9 ]' q( k3 n8 P' N% H/ R0 `8 i/ ~
│ │ │ 02_6-1.a_II__15-25_0_.pdf ]5 ~* W& {$ t' ^
│ │ │ 02_6-1.a_II__15-25_1_.pdf, o D. k. p9 Y$ p; s k
│ │ │ 02_6-1.a_II__15-25_2_.pdf
3 i: L+ w7 ]- ~. C Z( p │ │ │ 03_6-1.b_II__16-08.mp4
9 _6 R: l4 f1 [7 y) \8 S# x │ │ │ 04_6-1.c_II__17-16.mp42 z* ^2 I2 p, L. I0 z; }
│ │ │ 05_6-1.d_II__5-40.mp44 K) g$ y$ `7 z1 h+ c2 W/ w9 C U
│ │ │ 06_6-2.a_I__16-35.mp4
! @! L5 q; y7 E% E │ │ │ 07_6-2.b_I__10-41.mp44 N2 ~% ]9 E" M. d- ~2 I
│ │ │ 08_6-2.c_I__16-44.mp4
' n% n: Z# R& w0 y$ o& m& t │ │ │ 09_6-2.d_I__14-30.mp4
) M. S+ M K! w. }& w& @ │ │ │
6 J0 P9 g% Z1 f9 p2 n/ Q* } │ │ ├─07_Week_7# _: p% Y, q* D5 Z
│ │ │ 01_7-0.mp4
! B$ B V o* o$ t- ^7 T │ │ │ 02_7-1.a_II__14-31.mp4! `: a5 H0 N& f+ t# V0 P2 f" i6 }
│ │ │ 02_7-1.a_II__14-31.pdf
/ z! k, q9 f9 |, C │ │ │ 02_7-1.a_II__14-31_0_.pdf
! C& J; x9 _, N2 S' g4 C │ │ │ 02_7-1.a_II__14-31_1_.pdf# u2 F; n7 p9 N6 J& V
│ │ │ 02_7-1.a_II__14-31_2_.pdf
. k5 R' K) N* s" A; e" M │ │ │ 03_7-1.b_II__13-07.mp4; Q8 h0 ?0 k" c- z( W, K
│ │ │ 04_7-2.a-___10-35.mp4, r; _0 I' U- ]3 X4 {7 d8 O
│ │ │ 05_7-2.b-___08-42.mp4
& U0 e+ K: k; L/ l* ~" G │ │ │ 06_7-3.a-___15-07.mp4+ m' b% R+ M) N9 P6 s, Q* X, \
│ │ │ 07_7-3b-___19-20.mp4
$ ^( |5 R' r, e) | │ │ │ 9 n# v8 m- H9 v/ _: K3 E
│ │ ├─08_Week_81 L% k; V/ z! z! b# Q9 o; z$ e
│ │ │ 01_8-0.mp4
/ u8 c% R, f( e' y: ~; |( F, F │ │ │ 02_8-1.a__14-36.mp4
5 s3 b. I1 H! k) e+ {- P │ │ │ 02_8-1.a__14-36.pdf
* c$ W i) |0 h& B │ │ │ 02_8-1.a__14-36_0_.pdf1 K) Z* h4 Q4 z# J$ O2 T1 p: A
│ │ │ 02_8-1.a__14-36_1_.pdf
! p; }* D$ o: q! T$ i } │ │ │ 02_8-1.a__14-36_2_.pdf, [. T0 A3 ]$ A
│ │ │ 03_8-1.b__15-05.mp4, j0 O' ?8 D, k; }
│ │ │ 04_8-1.c__17-00.mp4
7 J R0 n5 l [, v' @! K │ │ │ 05_8-1.d__11-18.mp46 Z. J3 ^. K, M0 u+ d- m/ J* t; n
│ │ │ 06_8-2_12-32.mp4) z2 u+ F! F/ E" t, ?' D
│ │ │ 07_8-3.a__10-06.mp41 f- o* G5 T1 ?6 h! `, g9 d7 _0 U2 V
│ │ │ 08_8-3.b__17-27.mp4
" h0 `( b4 s6 H; V+ c* l │ │ │
) ^+ R; H- e9 u- _. @& w │ │ └─09_Week_99 z' H) l7 ^4 B/ B. c6 J; h
│ │ 01_9-1.a__11-18.mp4* y/ F( J) q4 O3 V
│ │ 01_9-1.a__11-18.pdf8 q. m O9 m( b+ U. @
│ │ 01_9-1.a__11-18_0_.pdf
5 E# f( R% ~6 |: U4 F* c5 j │ │ 01_9-1.a__11-18_1_.pdf# V" H1 v- F1 f& ]
│ │ 01_9-1.a__11-18_2_.pdf: B8 u6 @, Y: T9 u6 y
│ │ 02_9-1.b__13-49.mp4
; ^) A! r: k1 ]" N) F3 D6 ?/ W │ │ 03_9-2.aMGF__10-17.mp4
9 c3 w. [, k: |$ i │ │ 04_9-2.bMGF__14-06.mp49 M. B( K2 ]! J% \% G
│ │ 05_9-2.cMGF__15-53.mp4
7 t3 v+ b, o, U' Y, l1 u5 y9 u q │ │ 06_9-3.a__10-35.mp4
- Z, M( d2 M% z! K: a │ │ 07_9-3.b__13-01.mp4
+ m$ @7 p% X; l$ L0 Z& M2 J │ │ 08_9-4.a-__16-45.mp4
5 y' A9 E; i2 S) m! S1 a! w. ?7 m │ │ 09_9-4.b-__17-19.mp4
+ B/ x3 ?6 \7 C9 H5 i% Y+ Z, }' M │ │
! W" |6 M; o7 N" h. D* } │ └─概率-台大* N8 j: B. K7 P0 a* k8 {# c
│ │ 02-8.R4 Y% m! ~" g \8 b
│ │
- M- F" c( H" ^. v5 |7 n$ j │ ├─1& J% Z5 T i5 E0 A" Y
│ │ Benson_Coursera_Week_1_簡.pdf- d' y1 c# h: ]+ W
│ │ Benson_Coursera_Week_1_繁.pdf
3 H2 d. B2 B9 u8 E2 Z+ v, D$ a │ │ Benson_Coursera_Week_1_繁空.pdf
/ s# F6 E9 C: S" F │ │ 2 - 1 - 1-0：咱們先聊聊，這是門什麼樣的課呢-.mp4
. T9 i- K( j+ N S+ | │ │ 2 - 2 - 1-1：機率概論 (17-41).mp4- A1 l( n- w) T- d' x8 S- P1 i6 q
│ │ 2 - 3 - 1-2.a：集合論 (上) (11-46).mp4
" [. F% M$ p- S" D │ │ 2 - 4 - 1-2.b：集合論 (下) (09-40).mp42 f+ N* V# X/ Z8 M" n2 Q$ B$ }+ K% P$ ~& t
│ │ 2 - 5 - 1-3.a：機率名詞 (上) (11-24).mp4
3 n1 i" t9 F: u$ M' p- s/ f │ │ 2 - 6 - 1-3.b：機率名詞 (下) (16-36).mp4! G! I5 F* h; T2 l) a _9 E8 W
│ │
( e$ t- C# `: O │ ├─23 B* f0 C2 N- H L
│ │ Benson_Coursera_Week_2_簡.pdf* d0 j6 }. I8 j5 m: x
│ │ Benson_Coursera_Week_2_簡空.pdf9 p) G z; |8 Q0 w7 a! @
│ │ Benson_Coursera_Week_2_繁.pdf6 \9 ?* b% ~5 U" N1 [
│ │ Benson_Coursera_Week_2_繁空.pdf
- a1 _+ I. ?+ Z% v │ │ 3 - 1 - 2-0：咱們聊聊，是學習，還是應付- (15-32).mp4
3 }& a6 Z# n) k" {9 \. v3 `$ ^ │ │ 3 - 2 - 2-1.a：機率公理性質 (上) (16-09).mp4$ L4 s& N# U* B2 v* |
│ │ 3 - 3 - 2-1.b：機率公理性質 (中) (16-06).mp4
- J2 r9 ~' M G! ^7 D- w- A$ R │ │ 3 - 4 - 2-1.c：機率公理性質 (下) (10-07).mp4
1 v: w! Y* Y, D& A │ │ 3 - 5 - 2-2.a：條件機率 (上) (10-41).mp4
/ a0 {0 G/ T4 A1 G# m) U │ │ 3 - 6 - 2-2.b：條件機率 (中) (12-43).mp4( A; d$ j$ W& |" ]; N* ^
│ │ 3 - 7 - 2-2.c：條件機率 (下) (16-02).mp4
, a% v+ S/ O" V3 \6 l, C/ \: I │ │
8 x, N; d! h0 r. O; o │ ├─3
* t! Z$ }4 x& A0 w- _3 M │ │ Benson_Coursera_Week_3_簡.pdf" k& t3 k3 I, M6 D9 u
│ │ Benson_Coursera_Week_3_簡空.pdf; O; [' l$ q( A n. y# c3 j/ H& D
│ │ Benson_Coursera_Week_3_繁.pdf
8 ~7 s4 _8 Y$ b9 w) |7 `: o U! h/ l │ │ Benson_Coursera_Week_3_繁空.pdf
# U1 X. G9 B: m │ │ 4 - 1 - 3-0：咱們聊聊，常見的錯誤？學習的關鍵？ (16-46).mp4 ^5 A1 F9 e+ D. d3 m% w
│ │ 4 - 2 - 3-1.a：機率的獨立性 (上) (09-12).mp4
2 z7 x! X+ b- [1 i) w6 D │ │ 4 - 3 - 3-1.b：機率的獨立性 (下) (10-35).mp4$ V5 }' V0 I' ^' s$ l
│ │ 4 - 4 - 3-2：圖解繁複機率 (08-47).mp4
[& M9 q1 [; K! l. m' Q' a# V+ } │ │ 4 - 5 - 3-3.a：數數算機率 (上) (16-57).mp4
% S# q9 d4 E3 k0 g# _3 g( L( ? │ │ 4 - 6 - 3-3.b：數數算機率 (下) (12-58).mp4* P/ d/ [: r. R* h' }0 `
│ │
8 _& N8 v( q; o7 Q3 k3 |+ ? │ ├─4
8 ~( X& k1 ^" V6 O- {# L │ │ Benson_Coursera_Week_4_簡.pdf
6 Q' [; x+ t& r( q7 b │ │ Benson_Coursera_Week_4_簡空.pdf
+ i% p$ u: Z, g+ F │ │ Benson_Coursera_Week_4_繁.pdf
1 `6 g* l/ o! y. C/ f; s* C │ │ Benson_Coursera_Week_4_繁空.pdf
0 A2 |. c5 C2 e( D: `- y% @% c1 l w │ │ 5 - 1 - 4-0：咱們聊聊，如何幫自己面對未來挑戰？ (17-33).mp4
7 r$ W L! Z0 [( M7 M" E' p. W; y │ │ 5 - 10 - 4-4.b：離散機率分佈 I (下) (8-47).mp4
! `# a$ o8 O8 [ │ │ 5 - 2 - 4-1.a：隨機變數 (上) (13-53).mp41 W( V0 d: z! X L4 F
│ │ 5 - 3 - 4-1.b：隨機變數 (中) (14-43).mp4$ s m/ |5 D, O+ Z# V
│ │ 5 - 4 - 4-1.c：隨機變數 (下) (5-18).mp4
+ n* `; H0 A% M, i │ │ 5 - 5 - 4-2.a：累績分佈函數 CDF (上) (9-48).mp43 R/ X2 B3 b" ?) l$ c& D
│ │ 5 - 6 - 4-2.b：累績分佈函數 CDF (中) (8-59).mp4
1 @$ K2 V& I! ^+ U │ │ 5 - 7 - 4-2.c：累績分佈函數 CDF (下) (9-00).mp4
, L, x! z" I% `/ {+ | │ │ 5 - 8 - 4-3：機率質量函數 PMF (11-26).mp4
7 q _2 H0 a0 y r │ │ 5 - 9 - 4-4.a：離散機率分佈 I (上) (14-41).mp4
$ j3 K9 q- o" a- m: H+ m% `8 u │ │ * K8 [: O; G2 D6 o* |2 P
│ ├─5
5 L: S% U, c/ o4 B! ^ │ │ Benson_Coursera_Week_5_簡.pdf( t7 u, {+ R, T8 D2 h- a+ v+ [- o
│ │ Benson_Coursera_Week_5_簡空.pdf
6 `0 {4 L# @+ z! F │ │ Benson_Coursera_Week_5_繁.pdf6 T" H0 K; [! e' S/ M H2 } L
│ │ Benson_Coursera_Week_5_繁空.pdf, D: u' J& h5 ?6 [) O7 J
│ │ 6 - 1 - 5-0：咱們聊聊，願你夜夜好眠到天明！ (14-09).mp4
- B" w* o5 H, U4 V$ E* t6 z. c: Z │ │ 6 - 2 - 5-1.a：離散機率分佈 II (上) (10-36).mp4
8 P6 j1 a6 |( i3 [8 G; p │ │ 6 - 3 - 5-1.b：離散機率分佈 II (中) (12-06).mp4; e0 _* ^0 A! [* ^) o6 C% W
│ │ 6 - 4 - 5-1.c：離散機率分佈 II (下) (20-28).mp4
. E; f* N; S4 e │ │ 6 - 5 - 5-2：機率密度函數 PDF (18-56).mp4* q% G2 j8 ^, O, I. \ Z# V8 u
│ │ 6 - 6 - 5-3：連續機率分佈 I (18-12).mp41 |) L' M5 Q+ N9 A
│ │
6 @1 Z1 v8 [* F: Q, a6 Z │ ├─6' k d+ y7 S+ p1 g! M, }
│ │ Benson_Coursera_Week_6_簡.pdf
; g, K2 f. N8 x* \7 } │ │ Benson_Coursera_Week_6_簡空.pdf
! l6 t* j$ i/ f │ │ Benson_Coursera_Week_6_繁.pdf
6 Y0 \/ W4 l: _! Q │ │ Benson_Coursera_Week_6_繁空.pdf
3 z2 t1 w8 }# g │ │ 7 - 1 - 6-0：咱們聊聊，成功者的條件是什麼？ (10-13).mp4 ~3 Q; ^) y+ J/ ^3 a4 @
│ │ 7 - 2 - 6-1.a：連續機率分佈 II (上) (15-25).mp4! @4 R; F6 a0 f' ?" o. _
│ │ 7 - 3 - 6-1.b：連續機率分佈 II (中) (16-08).mp4
, h9 O3 a r( s' G S T0 ? │ │ 7 - 4 - 6-1.c：連續機率分佈 II (下) (17-16).mp4
, t$ O# M' }; { │ │ 7 - 5 - 6-1.d：連續機率分佈 II (末) (5-40).mp4: {# R7 ~- _& r$ I' T6 F/ G( F
│ │ 7 - 6 - 6-2.a：期望值 I (上) (16-35).mp4
6 z1 b* V) v' q0 c& ` │ │ 7 - 7 - 6-2.b：期望值 I (中) (10-41).mp4
, k4 d) m* M- f │ │ 7 - 8 - 6-2.c：期望值 I (下) (16-44).mp46 h; P9 ?( F+ M# r. a* F. o
│ │ 7 - 9 - 6-2.d：期望值 I (末) (14-30).mp44 H' S% c' c8 n% T: x6 O4 {
│ │ 7 r2 e Q0 H2 W' G* T9 g
│ ├─7
i" V- l: x. X. Z9 O6 i0 L │ │ Benson_Coursera_Week_7_簡.pdf0 C( w4 T) o' e! W
│ │ Benson_Coursera_Week_7_簡空.pdf
; I5 Z- m; `% D% I │ │ Benson_Coursera_Week_7_繁.pdf
5 E; g* W2 Q3 t │ │ Benson_Coursera_Week_7_繁空.pdf
2 ^, H+ X+ H1 P( e7 t/ Y, E │ │ 8 - 1 - 7-0：咱們聊聊，每天都在忙，忙的有用嗎？.mp4
4 Z/ C# d- U; ]" D- k │ │ 8 - 2 - 7-1.a：期望值 II (上) (14-31).mp4
3 c6 F5 [* w& H │ │ 8 - 3 - 7-1.b：期望值 II (下) (13-07).mp47 P" j$ |& i( K9 d2 e# R" ^
│ │ 8 - 4 - 7-2.a- 隨機變數之函數 (上) (10-35).mp4
& K5 u9 }" q, V- | │ │ 8 - 5 - 7-2.b- 隨機變數之函數 (下) (08-42).mp4
$ F; s9 D$ c* Y! ]* _6 ?0 Z │ │ 8 - 6 - 7-3.a- 條件機率分佈與失憶性 (上) (15-07).mp4
0 ?! O7 p' v7 K5 C% C& J4 L │ │ 8 - 7 - 7-3b- 條件機率分佈與失憶性 (下) (19-20).mp4. F+ V( Z" o& f- f# d7 j5 {
│ │ 0 k3 z/ j M+ Q3 d/ `- m& x3 }
│ ├─8' x8 m, _1 I+ S4 y2 l, E
│ │ Benson_Coursera_Week_8_簡.pdf
, w7 r" Z/ d& A/ |; u* k" b │ │ Benson_Coursera_Week_8_簡空.pdf
7 ~+ c$ V% \0 h" ^ │ │ Benson_Coursera_Week_8_繁.pdf
' B5 B* P5 E& l# N" o6 G* e( F │ │ Benson_Coursera_Week_8_繁空.pdf
0 r. {- p$ X9 L% @6 \9 m │ │ 9 - 1 - 8-0：咱們聊聊，如何探索有意義的人生？.mp4; d6 s& n0 F& d. m" ~
│ │ 9 - 2 - 8-1.a：聯合機率分佈 (上) (14-36).mp4
# c. x q3 l: o' c# Q; k& A T │ │ 9 - 3 - 8-1.b：聯合機率分佈 (中) (15-05).mp4
" W, W3 N% Z% N5 E4 |# E, F8 G │ │ 9 - 4 - 8-1.c：聯合機率分佈 (下) (17-00).mp4
/ f" h0 R# ?7 `+ N7 ^; j │ │ 9 - 5 - 8-1.d：聯合機率分佈 (末) (11-18).mp4
2 x8 L" D" m$ J+ L0 q │ │ 9 - 6 - 8-2：邊際機率分佈 (12-32).mp40 _9 i S" y- T8 r9 r
│ │ 9 - 7 - 8-3.a：雙變數期望值 (上) (10-06).mp48 K4 Z M7 U7 t, k( O# z# [
│ │ 9 - 8 - 8-3.b：雙變數期望值 (下) (17-27).mp4$ K6 j$ U8 K! T
│ │
5 K6 n f* _- l3 z% p │ └─9
8 r# I% A! K" k9 i. o# I │ Benson_Coursera_Week_9_簡.pdf. O; u" P; U& g9 w8 K* U
│ Benson_Coursera_Week_9_簡空.pdf4 a& ^ f+ u% [5 {
│ Benson_Coursera_Week_9_繁.pdf f R; E1 r8 i
│ Benson_Coursera_Week_9_繁空.pdf
/ l, n6 u% o& w/ M; E+ Y │ 10 - 1 - 9-1.a：隨機變數之和 (上) (11-18).mp4% h3 a' x# G6 d: A, r
│ 10 - 2 - 9-1.b：隨機變數之和 (下) (13-49).mp4
) S' i5 }+ |/ |1 V4 Z# Z2 C │ 10 - 3 - 9-2.a：MGF (上) (10-17).mp4( [; l2 N) R, I
│ 10 - 4 - 9-2.b：MGF (中) (14-06).mp4
8 A3 @! _/ ?& K+ a4 e: L* E │ 10 - 5 - 9-2.c：MGF (下) (15-53).mp41 W) ^- F8 k% ?* o
│ 10 - 6 - 9-3.a：多個隨機變數和 (上) (10-35).mp4
# H* ^4 k$ q, z' }7 d: d │ 10 - 7 - 9-3.b：多個隨機變數和 (下) (13-01).mp4% s8 X8 y! L$ j, H; W* k. [1 ?
│ 10 - 8 - 9-4.a：中央極限定理-萬佛朝宗 (上) (16-45).mp4
- V2 H0 s N; V2 B, u │ 10 - 9 - 9-4.b：中央極限定理-萬佛朝宗 (下) (17-19).mp4
: \8 U! R- x8 _ │
6 S. R a0 B, |6 i. ^* @ ├─036_Coding the Matrix
0 r; m3 a1 G: Z" O% S$ G5 o( ? │ └─036_Coding the Matrix
! {9 a' i$ \/ j0 h3 R% H; e │ └─matrix-0029 ~) \0 z: d+ e
│ │ 下载说明.txt8 k3 _' w6 w j: `
│ │ 关注我们.png' z$ h4 j. B- N ]9 r
│ │ 攻城狮论坛=网络技术+编程视频.url
) S) K5 I# T$ n/ ~, S) \' ? │ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt
L( h2 T+ ?4 w- \3 Q, ~" g" G │ │
. [9 X9 K- [0 m+ [ │ ├─01_Week_0-_The_Function_and_the_Field8 G" M6 K& N) K/ @9 x" \
│ │ 01_Course_Introduction_Part_1__9-53.mp43 g- T+ x: q- }, P9 o1 ]% O5 {
│ │ 01_Course_Introduction_Part_1__9-53.srt
6 @! j+ C' I' Q │ │ 01_Course_Introduction_Part_1__9-53.txt
5 D! ~+ [$ G# |2 U! h. x │ │ 02_Course_Introduction_Part_2__8-49.mp4* C) T6 `* {# p
│ │ 02_Course_Introduction_Part_2__8-49.srt3 Y8 ^/ J2 K) b7 g
│ │ 02_Course_Introduction_Part_2__8-49.txt
2 S- G: ?9 U: O) z ]. U7 ` │ │ 03_The_Function-_The_function_and_other_preliminaries__20-55.mp4- Y0 Y* I: h+ a# o5 v# U ~
│ │ 03_The_Function-_The_function_and_other_preliminaries__20-55.pdf
6 Y g) i' p% _/ R' ~- \: c │ │ 03_The_Function-_The_function_and_other_preliminaries__20-55.srt. I9 O( S. O1 Y
│ │ 03_The_Function-_The_function_and_other_preliminaries__20-55.txt
0 O& s; T! P) v4 s; V │ │ 04_The_Field-_Introduction_to_complex_numbers__5-52.mp4
/ B; @# h- o0 _* v' t │ │ 04_The_Field-_Introduction_to_complex_numbers__5-52.pdf
1 m3 |+ v5 V% y) s: b4 e. l │ │ 04_The_Field-_Introduction_to_complex_numbers__5-52.srt) K3 f O0 I: C4 r0 V
│ │ 04_The_Field-_Introduction_to_complex_numbers__5-52.txt' }3 D7 T6 ?6 G0 d2 {
│ │ 05_The_Field-_Playing_with_C_15-19.mp4
: E* o' t8 @3 q, H" x │ │ 05_The_Field-_Playing_with_C_15-19.pdf
; g! ^2 h! v8 }' i, o6 Z. [0 ^$ Q │ │ 05_The_Field-_Playing_with_C_15-19.srt
# b0 _- I& y2 i. Z8 \ │ │ 05_The_Field-_Playing_with_C_15-19.txt
! u. h3 e( _2 B- Z/ m- r w │ │ 06_The_Field-_Playing_with_GF2__10-28.mp4
: Z$ s: [( E0 R4 w2 [ │ │ 06_The_Field-_Playing_with_GF2__10-28.pdf
5 J/ {2 m' v) t' |/ {/ ]+ U6 | │ │ 06_The_Field-_Playing_with_GF2__10-28.srt9 t L$ H l% d
│ │ 06_The_Field-_Playing_with_GF2__10-28.txt! [* u1 D- D3 B
│ │ : g) \0 _8 n) h
│ ├─02_Week_1-_The_Vector5 @/ a8 z: Z- C0 z
│ │ 01_The_Vector-_What_is_a_vector__8-20.mp45 k1 o1 ? p b5 |6 M
│ │ 01_The_Vector-_What_is_a_vector__8-20.pdf
* ~( |" r0 x* w6 _0 x4 o │ │ 01_The_Vector-_What_is_a_vector__8-20.srt( }5 K& b" r, \* B' y
│ │ 01_The_Vector-_What_is_a_vector__8-20.txt
2 J/ \, `3 P k" Y1 o# ?6 t │ │ 02_The_Vector-_Vector_addition_and_scalar-vector_multiplication__10-16.mp49 i% a% a, q% ~& P$ P/ G
│ │ 02_The_Vector-_Vector_addition_and_scalar-vector_multiplication__10-16.pdf
( A( U4 L, R2 v" {8 L9 \9 n │ │ 02_The_Vector-_Vector_addition_and_scalar-vector_multiplication__10-16.srt
; o. k( o1 z" b) u5 M │ │ 02_The_Vector-_Vector_addition_and_scalar-vector_multiplication__10-16.txt
2 N# D/ W2 u: f; r4 K: N2 s │ │ 03_The_Vector-_Dictionary-based_representations_of_vectors__9-10.mp47 M3 y' n, l$ Q7 r
│ │ 03_The_Vector-_Dictionary-based_representations_of_vectors__9-10.pdf
& Q( B2 z9 F# Y3 d H' Z │ │ 03_The_Vector-_Dictionary-based_representations_of_vectors__9-10.srt
. l1 Q: {1 u8 A, b/ o │ │ 03_The_Vector-_Dictionary-based_representations_of_vectors__9-10.txt) _; X$ |2 G) w$ f: h ]- x. s' ~
│ │ 04_The_Vector-_Vectors_over_GF2__9-18.mp4
?, @6 _ Q4 f2 h6 j4 y │ │ 04_The_Vector-_Vectors_over_GF2__9-18.pdf
( ]9 C- S* a8 \( i# a │ │ 04_The_Vector-_Vectors_over_GF2__9-18.srt1 I0 f0 b1 [* n' U+ b: E
│ │ 04_The_Vector-_Vectors_over_GF2__9-18.txt
% \$ U* J7 h$ |8 e+ |' c │ │ 05_The_Vector-_Dot-product__8-49.mp4
5 |4 w3 ] V6 i o. C2 v7 U │ │ 05_The_Vector-_Dot-product__8-49.pdf2 @9 g( L& f, w- \8 b
│ │ 05_The_Vector-_Dot-product__8-49.srt
" I; n7 \1 c& ~) |. H │ │ 05_The_Vector-_Dot-product__8-49.txt, q3 ^2 ~3 f4 }7 H w! `9 I
│ │ 06_The_Vector-_Dot-product_of_vectors_over_GF2__4-44.mp4! _7 y* R( O- @; y8 R' C
│ │ 06_The_Vector-_Dot-product_of_vectors_over_GF2__4-44.pdf
2 t& z8 y" ?/ q$ [9 o │ │ 06_The_Vector-_Dot-product_of_vectors_over_GF2__4-44.srt
* V5 ~ s$ s; ?- A% i5 u) r" ~& z' p8 V2 ~ │ │ 06_The_Vector-_Dot-product_of_vectors_over_GF2__4-44.txt7 Y0 @ B" J1 o+ m4 C* C& }7 T
│ │ 07_The_Vector-_Solving_a_triangular_system_of_linear_equations__4-00.mp4
9 F( j! N ^$ T0 ` D% d │ │ 07_The_Vector-_Solving_a_triangular_system_of_linear_equations__4-00.pdf
- U, _1 d% F! k, g }: C b C │ │ 07_The_Vector-_Solving_a_triangular_system_of_linear_equations__4-00.srt# U" [/ ] w& H( t) | [ `7 r
│ │ 07_The_Vector-_Solving_a_triangular_system_of_linear_equations__4-00.txt
( i5 s0 G: X. @: m9 `7 P$ Y │ │ 9 |% D+ Z' v: Z: \
│ ├─03_Week_2-_The_Vector_Space
, w" o! G1 w9 e2 u& Z" H │ │ 01_The_Vector_Space-_Linear_combinations.mp4
. z \6 _' F0 F: s2 U+ L+ @ │ │ 01_The_Vector_Space-_Linear_combinations.pdf
* j+ n- S3 k- k* C3 H% g8 E; B │ │ 01_The_Vector_Space-_Linear_combinations.srt# B( E& u- _3 M$ d6 T, M
│ │ 01_The_Vector_Space-_Linear_combinations.txt
# l& |/ v1 d. h │ │ 02_The_Vector_Space-_Span.mp4: d7 P2 i" w5 d9 o+ W
│ │ 02_The_Vector_Space-_Span.pdf2 ?; D4 C t% Q" L0 J
│ │ 02_The_Vector_Space-_Span.srt
6 S6 f: ]: d7 u: ]/ c- q │ │ 02_The_Vector_Space-_Span.txt' V8 M9 u. q' h; M5 i
│ │ 03_The_Vector_Space-_Geometry_of_Sets_of_Vectors.mp4% u; `/ a+ S3 x. u
│ │ 03_The_Vector_Space-_Geometry_of_Sets_of_Vectors.pdf- b, Y: k7 P; J
│ │ 03_The_Vector_Space-_Geometry_of_Sets_of_Vectors.srt* ?) E2 n; Y( S9 n
│ │ 03_The_Vector_Space-_Geometry_of_Sets_of_Vectors.txt
3 H* c( A# P9 ~% m; G. r │ │ 04_The_Vector_Space-_Vector_spaces.mp4# m" T- J7 V! |# e( m. v7 c
│ │ 04_The_Vector_Space-_Vector_spaces.pdf, D$ ~- O7 x2 k( k# s5 v
│ │ 04_The_Vector_Space-_Vector_spaces.srt
! y3 |8 R3 ~: ?: c! |: e │ │ 04_The_Vector_Space-_Vector_spaces.txt# @- Q. t& Y" Q9 J; b. |$ N
│ │ 05_The_Vector_Space-_Checksum_function.mp4
: f# g- \/ v' A+ |/ V! P │ │ 05_The_Vector_Space-_Checksum_function.pdf' ^, D: y, Q' z- C6 w$ @5 _3 G
│ │ 05_The_Vector_Space-_Checksum_function.srt
; X5 P1 \; F' t │ │ 05_The_Vector_Space-_Checksum_function.txt7 i7 ?3 {. T) B+ J$ V2 e) n9 R
│ │ ; X% O" l4 j5 @& Z
│ ├─04_Week_3-_The_Matrix3 N4 s, S( }0 H" E+ m1 ?+ ?
│ │ 01_The_Matrix-_What_is_a_matrix.mp45 s4 I+ B/ s7 b1 ?
│ │ 01_The_Matrix-_What_is_a_matrix.pdf" L5 T N" L' Y5 F& g
│ │ 01_The_Matrix-_What_is_a_matrix.srt" `2 Z$ ^, g3 q& w9 c! l
│ │ 01_The_Matrix-_What_is_a_matrix.txt0 {& Q2 G: v8 U1 w
│ │ 02_The_Matrix-_Matrix-vector_and_vector-matrix_multiplication.mp4
1 e3 o8 u# v/ W2 D# _: C& [4 k │ │ 02_The_Matrix-_Matrix-vector_and_vector-matrix_multiplication.pdf
o2 d! B0 L D6 c4 t2 n" N: X( S$ S │ │ 02_The_Matrix-_Matrix-vector_and_vector-matrix_multiplication.srt
7 C0 d4 `- s; d [ │ │ 02_The_Matrix-_Matrix-vector_and_vector-matrix_multiplication.txt j; U' ~* l/ _5 L, s/ k0 V% n. ~1 h
│ │ 03_The_Matrix-_Matrix-vector_multiplication_in_terms_of_dot-products.mp4
; I( \. e! e! n │ │ 03_The_Matrix-_Matrix-vector_multiplication_in_terms_of_dot-products.pdf: }6 @2 R* h" ]. Y* y& k
│ │ 03_The_Matrix-_Matrix-vector_multiplication_in_terms_of_dot-products.srt2 Z$ D5 R: C0 Z# e
│ │ 03_The_Matrix-_Matrix-vector_multiplication_in_terms_of_dot-products.txt! L x: Q$ i; f9 d
│ │ 04_The_Matrix-_Null_space.mp4
! h/ I% q* a% n' W7 {" X- ? │ │ 04_The_Matrix-_Null_space.pdf0 Q4 p+ V7 V! [) a% K$ j- w% T
│ │ 04_The_Matrix-_Null_space.srt1 f6 O. I5 Q6 S# }
│ │ 04_The_Matrix-_Null_space.txt4 [( \6 l; ?5 h2 t8 y
│ │ 05_The_Matrix-_Error-correcting_codes.mp4: J( k# R8 e% {: Q, }
│ │ 05_The_Matrix-_Error-correcting_codes.pdf2 V; S: }/ G' L5 r( p0 i
│ │ 05_The_Matrix-_Error-correcting_codes.srt6 c2 J# K7 ~( h3 h4 P& U' ^
│ │ 05_The_Matrix-_Error-correcting_codes.txt
c8 D" T+ O( p9 q │ │ 06_The_Matrix-_Matrices_and_their_functions.mp4
3 y. \' P7 v+ z' H1 T │ │ 06_The_Matrix-_Matrices_and_their_functions.pdf# b7 Q4 Y7 O6 _/ b8 l0 O
│ │ 06_The_Matrix-_Matrices_and_their_functions.srt. U1 F& I# A) F& o
│ │ 06_The_Matrix-_Matrices_and_their_functions.txt+ |- Y' a3 ]8 ]+ @" C
│ │ 07_The_Matrix-_Linear_functions.mp4
- G1 _; F3 T; ]% D │ │ 07_The_Matrix-_Linear_functions.pdf+ W0 P# @3 R2 m) W# J+ n0 u: K' l* Y
│ │ 07_The_Matrix-_Linear_functions.srt
' _7 n4 y9 G1 V$ T+ ?4 P2 z/ a0 j │ │ 07_The_Matrix-_Linear_functions.txt/ ^4 U m q& B9 W1 A6 E
│ │ 08_The_Matrix-_Matrix-matrix_multiplication.mp4
1 i5 L: _: { E W │ │ 08_The_Matrix-_Matrix-matrix_multiplication.pdf$ r1 Z$ v1 z' O( ~
│ │ 08_The_Matrix-_Matrix-matrix_multiplication.srt
& R B: F0 c: O, f9 J/ } │ │ 08_The_Matrix-_Matrix-matrix_multiplication.txt
& k* X. N; L* T │ │ 09_The_Matrix-_Matrix-matrix_multiplication_and_function_composition.mp49 c4 V% z( [4 p) n" C2 |
│ │ 09_The_Matrix-_Matrix-matrix_multiplication_and_function_composition.pdf
9 h/ a3 W1 c0 H: H$ {0 c │ │ 09_The_Matrix-_Matrix-matrix_multiplication_and_function_composition.srt& b% G" m" }& E6 x! J
│ │ 09_The_Matrix-_Matrix-matrix_multiplication_and_function_composition.txt
3 `' f" k8 ^* p │ │ 10_The_Matrix-_Matrix_inverse.mp4. q3 `3 T f$ e
│ │ 10_The_Matrix-_Matrix_inverse.pdf
; F; f3 C3 `0 g E: o( ~ │ │ 10_The_Matrix-_Matrix_inverse.srt
& K0 [0 B0 ]1 k7 G* N. a │ │ 10_The_Matrix-_Matrix_inverse.txt& C9 z ^4 @" L# R6 l
│ │
3 k& L; O, c3 q# p) e1 y │ ├─05_Week_4-_The_Basis* l1 G0 _' `. T& i7 z
│ │ 01_The_Basis-_Coordinate_systems.mp4: [; C& @% Z3 k D0 Z
│ │ 01_The_Basis-_Coordinate_systems.pdf
; c$ ~9 I$ v5 X │ │ 01_The_Basis-_Coordinate_systems.srt
g: K& ]+ k, \+ N6 B, J& X T │ │ 01_The_Basis-_Coordinate_systems.txt
0 |& {7 j: C9 d, Z- h6 n │ │ 02_The_Basis-_Lossy_compression.mp4
; O. B8 h2 f& z4 X │ │ 02_The_Basis-_Lossy_compression.pdf
7 d' @3 i0 ?& V) x7 {8 i9 P/ v │ │ 02_The_Basis-_Lossy_compression.srt
: f! u( e' h: H │ │ 02_The_Basis-_Lossy_compression.txt% ^, [1 Y* c( }; Z8 C6 j
│ │ 03_The_Basis-_Algorithms_for_finding_a_set_of_generators.mp4% X4 q1 p+ K$ _6 p+ B' ?
│ │ 03_The_Basis-_Algorithms_for_finding_a_set_of_generators.pdf
/ P7 E& K$ Y: Z- e │ │ 03_The_Basis-_Algorithms_for_finding_a_set_of_generators.srt
4 l q4 B+ Z. c6 z- I# m0 G8 J │ │ 03_The_Basis-_Algorithms_for_finding_a_set_of_generators.txt9 t* B! G, ]( E1 i* x
│ │ 04_The_Basis-_Minimum_spanning_forest.mp4
$ m* E9 C$ N8 C! }3 z │ │ 04_The_Basis-_Minimum_spanning_forest.pdf6 A4 F- O R8 p( `" v! g' c# V ?
│ │ 04_The_Basis-_Minimum_spanning_forest.srt
3 x" T* J/ V% }- t( j │ │ 04_The_Basis-_Minimum_spanning_forest.txt% W, {) d( n: e0 [9 E5 k( U
│ │ 05_The_Basis-_Linear_dependence.mp4
, C+ A+ E q: }- G │ │ 05_The_Basis-_Linear_dependence.pdf9 ?4 m0 A. z% F- p y
│ │ 05_The_Basis-_Linear_dependence.srt1 w$ v$ y/ v) H1 e
│ │ 05_The_Basis-_Linear_dependence.txt e$ u, p; z# }# y, p8 W
│ │ 06_The_Basis-_Basis.mp4; k/ ]4 }! U; T* K8 ^8 L2 S1 l
│ │ 06_The_Basis-_Basis.pdf7 M# ?# X; P' m3 u. |3 t2 y
│ │ 06_The_Basis-_Basis.srt' d: C( l1 T" x0 [
│ │ 06_The_Basis-_Basis.txt" P) k! f, v* A& `* B
│ │ 07_The_Basis-_Unique_representation.mp4
9 V6 _7 C8 q( ?. ~ │ │ 07_The_Basis-_Unique_representation.pdf! M/ t4 ]6 G( F. ?: L+ D- x5 D
│ │ 07_The_Basis-_Unique_representation.srt
6 W0 Q% @6 V a$ s │ │ 07_The_Basis-_Unique_representation.txt
. O6 m0 v* u; F5 p │ │ 08_The_Basis-_Change_of_basis.mp46 o6 C( }' k0 j8 r& d! B
│ │ 08_The_Basis-_Change_of_basis.pdf# R* G5 \) t0 x, M
│ │ 08_The_Basis-_Change_of_basis.srt/ T, A! e. N$ E5 l
│ │ 08_The_Basis-_Change_of_basis.txt; e9 d; ^! t4 w3 ]% z2 v6 u! C$ Z
│ │ 09_The_Basis-_Perspective_rendering.mp4
7 J8 d: p/ o+ s1 |/ _: H) ] │ │ 09_The_Basis-_Perspective_rendering.pdf
2 P& s7 y4 e. w$ d% u2 ^ │ │ 09_The_Basis-_Perspective_rendering.srt6 d# P. k% S9 g: y Y
│ │ 09_The_Basis-_Perspective_rendering.txt
0 M7 v. D, y' C- f! m- ^ │ │ 10_The_Basis-_Perspective_rectification.mp4
! E% a4 g, K3 t' _# ^ │ │ 10_The_Basis-_Perspective_rectification.pdf
: p; z8 c0 ?$ E3 D) C+ e │ │ 10_The_Basis-_Perspective_rectification.srt
) w5 D7 a7 W* e" } │ │ 10_The_Basis-_Perspective_rectification.txt
) o9 ]! m4 ^- B │ │ 11_The_Basis-_The_Exchange_Lemma.mp4
0 G# B; m6 ]1 ] │ │ 11_The_Basis-_The_Exchange_Lemma.pdf
- z* G9 V' _0 y3 [ │ │ 11_The_Basis-_The_Exchange_Lemma.srt
5 {! Z' ~6 O8 r* T8 Z │ │ 11_The_Basis-_The_Exchange_Lemma.txt
8 p- V4 `1 ]- @# ]# s( m0 o& k; Z/ U" r │ │
& J* X; I8 N% W: B- Y6 m* \ │ ├─06_Week_5-_Dimension
1 t7 Z6 v6 x! q; |$ [. s) o( o9 R │ │ 01_Dimension-_The_size_of_a_basis.mp4
& s" l* c% y3 o │ │ 01_Dimension-_The_size_of_a_basis.pdf
- M% ?3 q$ g/ d! v+ A │ │ 01_Dimension-_The_size_of_a_basis.srt" ]6 ^- D0 \1 ?) T, E
│ │ 01_Dimension-_The_size_of_a_basis.txt
* g" C, c: j+ N │ │ 02_Dimension-_Dimension_and_rank_I.mp4: ?1 y6 @. k9 i8 p. G
│ │ 02_Dimension-_Dimension_and_rank_I.pdf
7 o% ?3 y$ d) n0 T │ │ 02_Dimension-_Dimension_and_rank_I.srt m! D: k. Y! L: `3 E- P, `
│ │ 02_Dimension-_Dimension_and_rank_I.txt
8 U0 e9 ^. A% t' Z) ~& s% j5 s# d │ │ 03_Dimension-_Dimension_and_rank_II.mp40 H7 H5 C7 X7 y
│ │ 03_Dimension-_Dimension_and_rank_II.pdf+ p9 L! J0 J% b% q1 d
│ │ 03_Dimension-_Dimension_and_rank_II.srt7 a: i! A* M7 X- g! k6 E
│ │ 03_Dimension-_Dimension_and_rank_II.txt8 {4 j* U8 _3 Y6 h* M! @5 c
│ │ 04_Dimension-_Direct_sum.mp45 Y; H' Y. ]2 I; O$ v
│ │ 04_Dimension-_Direct_sum.pdf
/ ?" E$ E' _/ s& u# Q1 A5 q+ F) u │ │ 04_Dimension-_Direct_sum.srt( B: c7 Z; e! k* x% V$ N
│ │ 04_Dimension-_Direct_sum.txt- X# q9 x1 g1 K9 i
│ │ 05_Dimension-_Dimension_and_linear_functions_I.mp4
+ S* h. b$ q/ @9 d0 M$ k2 g │ │ 05_Dimension-_Dimension_and_linear_functions_I.pdf3 g7 e) ]- ]" B( g
│ │ 05_Dimension-_Dimension_and_linear_functions_I.srt
/ k) K1 T2 V& l8 X3 S+ m. A │ │ 05_Dimension-_Dimension_and_linear_functions_I.txt
5 Z* a# M" L2 W, r& V3 W4 {! B │ │ 06_Dimension-_Dimension_and_linear_functions_II.mp4
; v# P0 C) y1 q+ T% q+ q1 ? │ │ 06_Dimension-_Dimension_and_linear_functions_II.pdf
, `+ [$ g; Z& |1 m │ │ 06_Dimension-_Dimension_and_linear_functions_II.srt: N8 Y- a/ ~) n
│ │ 06_Dimension-_Dimension_and_linear_functions_II.txt
1 K$ q' e* W. Y& W" g$ V │ │ 07_Dimension-_Two_representations_of_vector_spaces.mp4
( h7 y8 x1 U& x4 \ │ │ 07_Dimension-_Two_representations_of_vector_spaces.pdf. j. k+ |4 Q, C% h$ G
│ │ 07_Dimension-_Two_representations_of_vector_spaces.srt
. @4 ]3 G5 J; q( ?( t* r │ │ 07_Dimension-_Two_representations_of_vector_spaces.txt
0 \8 b/ v1 J7 L- N3 ^, b3 b' u: m │ │ 08_Dimension-_Threshold_secret_sharing.mp48 r- w+ k2 n0 x3 w, d* t+ N
│ │ 08_Dimension-_Threshold_secret_sharing.pdf
0 ^3 z2 |, k. E7 D; \ │ │ 08_Dimension-_Threshold_secret_sharing.srt
" O9 X2 U3 d) ]" p/ \ │ │ 08_Dimension-_Threshold_secret_sharing.txt
1 O1 Q: G5 [7 X; j+ ] │ │ 3 F2 q0 S8 P0 b4 i
│ ├─07_Week_6-_Gaussian_Elimination_and_the_Inner_Product
3 f3 U/ `# V# w3 d! q# J" b& z │ │ 01_Gaussian_Elimination-_Echelon_form.mp4
" K8 {2 o. D6 k* e5 Y; n │ │ 01_Gaussian_Elimination-_Echelon_form.pdf
, k& N2 r5 W" u/ D- x$ D6 {( d. p) j │ │ 01_Gaussian_Elimination-_Echelon_form.srt
. l0 ]0 A) v8 X8 ?6 h │ │ 01_Gaussian_Elimination-_Echelon_form.txt* r1 g9 a2 f7 ]& s% h
│ │ 04_Gaussian_Elimination-_Factoring_integers.mp4
% B/ w. b- x2 ? ~. ?1 c │ │ 04_Gaussian_Elimination-_Factoring_integers.pdf
s" k3 a8 j9 z, U8 Q) W6 J5 w: e │ │ 04_Gaussian_Elimination-_Factoring_integers.srt
/ n$ o- K: T( i+ O% R │ │ 04_Gaussian_Elimination-_Factoring_integers.txt
+ ]4 l+ W8 `$ _8 _, S │ │ 05_The_Inner_Product-_The_inner_product.mp4
7 T( n; ^5 P0 r: o │ │ 05_The_Inner_Product-_The_inner_product.pdf6 @" x/ ~1 C0 q5 a: |; a/ T
│ │ 05_The_Inner_Product-_The_inner_product.srt
* d! S2 \: a F# F, t2 u" l │ │ 05_The_Inner_Product-_The_inner_product.txt& j: m& b6 b$ I) d+ v
│ │ 06_The_Inner_Product-_Orthogonality.mp4
& u( q) h$ o2 Y- `+ I. ?" i k. H │ │ 06_The_Inner_Product-_Orthogonality.pdf5 C+ `8 l7 k- [& ~ ~: i# ]" {' f
│ │ 06_The_Inner_Product-_Orthogonality.srt4 r* u8 u5 S H6 D& R
│ │ 06_The_Inner_Product-_Orthogonality.txt4 g. F1 ]9 q) l- O, o* \
│ │
n+ Y: }* a% ~! d6 I/ a7 J. r( e2 J5 D, u │ ├─08_Week_7-_Orthogonalization
' P; R! \+ }1 w6 N+ U& r │ │ 01_Orthogonalization-_Finding_the_closest_point_in_a_plane.mp4
+ e! T( {4 S: Y │ │ 01_Orthogonalization-_Finding_the_closest_point_in_a_plane.pdf
' r/ n6 l# \5 Q3 L │ │ 01_Orthogonalization-_Finding_the_closest_point_in_a_plane.srt
2 X- p, _- n x. c. A: y) ]# e, b │ │ 01_Orthogonalization-_Finding_the_closest_point_in_a_plane.txt- t' i+ |; U) y( `8 J
│ │ 02_Orthogonalization-_Projection_orthogonal_to_multiple_vectors.mp4
! ^8 c2 H" I6 y- N │ │ 02_Orthogonalization-_Projection_orthogonal_to_multiple_vectors.pdf
1 s$ w; M/ W) T8 u6 x. p │ │ 02_Orthogonalization-_Projection_orthogonal_to_multiple_vectors.srt
$ E9 d- u% ~5 F0 b6 F$ {4 H( w │ │ 02_Orthogonalization-_Projection_orthogonal_to_multiple_vectors.txt+ Z7 G3 L1 Z2 |5 b6 M6 r! |
│ │ 03_Orthogonalization-_Building_an_orthogonal_set_of_generators.mp46 a& K7 W3 W- [1 t
│ │ 03_Orthogonalization-_Building_an_orthogonal_set_of_generators.pdf, L5 A/ H) x" E7 r' Z( P' ]
│ │ 03_Orthogonalization-_Building_an_orthogonal_set_of_generators.srt
; q! U+ i7 C R: I% \9 X. S* n │ │ 03_Orthogonalization-_Building_an_orthogonal_set_of_generators.txt; W, u9 Z6 k$ x
│ │ 04_Orthogonalization-_Computing_a_basis.mp42 p) w1 p! p2 |2 O; L
│ │ 04_Orthogonalization-_Computing_a_basis.pdf
" d) G. s2 B2 n6 j5 l% ^6 J │ │ 04_Orthogonalization-_Computing_a_basis.srt
; U$ R* H! t( e, H' _) y" V │ │ 04_Orthogonalization-_Computing_a_basis.txt
5 c0 z7 n G& g1 {8 k& j │ │ 05_Orthogonalization-_Orthogonal_complement.mp4. d" b Y. G, G$ E5 P! Q
│ │ 05_Orthogonalization-_Orthogonal_complement.pdf
5 h, e: k8 {/ t% H │ │ 05_Orthogonalization-_Orthogonal_complement.srt2 W! ?1 i! A) t7 ^) L3 O. E
│ │ 05_Orthogonalization-_Orthogonal_complement.txt
: h. n/ [, G+ ~5 t; f2 q │ │ 06_Orthogonalization-_Two_ways_to_find_a_basis_for_the_null_space.mp4
& [2 e2 \- B; F* _3 H+ J │ │ 06_Orthogonalization-_Two_ways_to_find_a_basis_for_the_null_space.pdf E+ B7 d1 t4 Q0 O6 X& y/ x/ i
│ │ 06_Orthogonalization-_Two_ways_to_find_a_basis_for_the_null_space.srt5 a0 N N1 y6 W) C3 m {, T2 L9 |9 G
│ │ 06_Orthogonalization-_Two_ways_to_find_a_basis_for_the_null_space.txt \5 V) H5 O3 L
│ │ 07_Orthogonalization-_The_QR_factorization.mp48 E( h- B4 [5 d) t) h
│ │ 07_Orthogonalization-_The_QR_factorization.pdf
( m& Z" s; Q* `+ V │ │ 07_Orthogonalization-_The_QR_factorization.srt
2 l$ I0 S, L) C. O. X2 p │ │ 07_Orthogonalization-_The_QR_factorization.txt+ S0 k3 F/ I; H3 S
│ │ 09_Orthogonalization-_Applications_of_least_squares.mp4
2 [, j, U9 T# w4 n │ │ 09_Orthogonalization-_Applications_of_least_squares.pdf6 b! R' ~5 N% N9 R$ J$ a% Z; K
│ │ 09_Orthogonalization-_Applications_of_least_squares.srt
1 g9 B- d+ I( | │ │ 09_Orthogonalization-_Applications_of_least_squares.txt0 }+ {$ J& W" L2 u& l! y; P
│ │ 8 [* b2 a8 ^- b! q, a
│ └─09_Tutorials: G1 k6 a: g" v! b
│ 01_How_to_submit_assignments.mp4( x k( q4 G- Q0 R- u7 ~
│ 01_How_to_submit_assignments.srt
" [0 r# q* X' Y4 {) Y │ 01_How_to_submit_assignments.txt
" D$ e# I; F+ l1 E │
% I* W4 A7 G5 d& S+ L ├─Big Data, Cloud Computing, & CDN Emerging Technologies
s3 S% d) A5 A" g' H! e$ r │ └─Big Data, Cloud Computing, & CDN Emerging Technologies
2 j8 s* J: L9 E │ │ 下载说明.txt' d1 ?: Q* I0 o9 i* k% Q4 w6 j
│ │ 关注我们.png
0 ` F! Z" M4 d4 |) {" @7 B │ │ 攻城狮论坛=网络技术+编程视频.url, \$ i! ]! E' K* ^4 L
│ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt" B% d+ g# N8 p
│ │
% z) ~# J7 s( z │ ├─01_cloud-computing: m9 r$ q, [0 O- ~
│ │ └─01_cloud-computing% y) i2 E- Z5 w# A. q+ D
│ ├─02_big-data$ o. K' x, `$ x, C
│ │ └─01_big-data/ u. |5 L& ?: Z9 j/ U9 y Z' F
│ │ 01_big-data-examples.mp4
, d- S Z7 y3 N │ │ 01_big-data-examples.srt/ G! t$ T9 A" o; l2 X; L! ]5 M
│ │ 02_big-datas-4-vs.mp4
' `* f5 N+ z! H$ E4 g8 x6 o3 _/ Y: g' Y │ │ 02_big-datas-4-vs.srt
, D: R; Y; a% d* C │ │ 03_hadoop.mp4
# d0 O& ~" z* q2 U │ │ 03_hadoop.srt" p* x B$ Q: O4 m( o
│ │ 04_mapreduce-vs-rdbms.mp4
' h# V- r) t: O* K# n4 {5 C │ │ 04_mapreduce-vs-rdbms.srt
# O/ _2 n) ~( J1 a9 g/ F/ y │ │ 05_mapreduce.mp4' S7 t4 R1 W4 K
│ │ 05_mapreduce.srt
/ U2 p, \ P0 G& m2 P* r5 `+ D │ │ 06_hdfs.mp42 [2 e+ _' c+ ?+ ]6 @* i8 B
│ │ 06_hdfs.srt( {! q/ q7 ]- r& _0 x, i
│ │
: Y! J* M; A# ?$ _1 J9 Z" p' i │ └─03_cdn-content-delivery-network
* E" y4 l( J7 W, A: R ├─Duke Image and video processing From Mars to Hollywood with a stop at the hospital* w' m, i7 t' f3 N }0 Z& F: w
├─Interactive Computer Graphics
1 t4 |' Z5 B+ E) t: b │ └─Interactive Computer Graphics4 |+ L- e+ u9 k5 Y$ O2 a* @
│ interactivegraphics-Torrent-Week1_All.zip.torrent$ s8 u2 l% Y: R" m2 r2 n
│ interactivegraphics-Torrent-Week2_All.zip.torrent
2 x+ Z& U6 l' x4 \& G" P │ interactivegraphics-Torrent-Week3_All.zip.torrent
# D$ F( m% W9 X# ^8 C# H │ interactivegraphics-Torrent-Week4_All.zip.torrent4 o9 \2 m: [! ?( z4 J0 I$ q1 o# X1 L
│ interactivegraphics-Torrent-Week5_All.zip.torrent
# `2 y$ q/ H4 r0 K │ interactivegraphics-Torrent-Week6_All.zip.torrent1 V/ c$ y+ B" R/ Q+ ]# x2 Q# }
│ interactivegraphics_Torrent_Week1_All.zip0 c7 t% l8 e; E B; E0 U7 e
│ interactivegraphics_Torrent_Week2_All.zip2 G- w3 g3 G" P8 Q" r0 z2 O
│ interactivegraphics_Torrent_Week3_All.zip
9 u2 z) o p, T! s; ], G2 B │ interactivegraphics_Torrent_Week4_All.zip
, r# V& c# d, O5 ^) [" b) }; A │ interactivegraphics_Torrent_Week5_All.zip0 w) w3 _8 [& j6 x/ ^7 o. @3 ]
│ 下载说明.txt, o+ _6 G& i+ a( \% _( A6 V
│ 关注我们.png0 {, a! U# \& T& j/ B
│ 攻城狮论坛=网络技术+编程视频.url( M4 @. y8 M3 C: T' |' X* ^
│ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt
% Q8 e, g, R/ M% t* i │
1 Q+ s1 N1 L) z1 _" l$ {6 z ├─Malik - Computer Vision; ~0 [4 V2 R7 x$ u: e
│ └─Malik - Computer Vision
' O5 P8 j4 T* P5 P │ 001_Overview.mp42 a' @) L1 \3 ]4 T0 q
│ 001_Overview.srt
5 @. Q# }% G c+ K- k │ 002_Fundamentals of image formation.mp4' v+ K9 G* s& e" I( B a
│ 002_Fundamentals of image formation.srt
& V6 t0 A+ g( u7 W' @* @ │ 003_Fundamentals of image formation - part II.mp4- j) \: y1 `- s/ R
│ 003_Fundamentals of image formation - part II.srt
: J% r! f, ]* q4 I7 D& c6 s, G │ 004_Rigid body motion.mp4$ A# W9 {8 r6 W0 ]( q2 j; G
│ 004_Rigid body motion.srt
7 f% z h4 _" `& w │ 005_Orthogonal transformations.mp4: o3 E7 t3 A7 C5 M/ Y' C
│ 005_Orthogonal transformations.srt/ a# L% R: n+ S5 w* V
│ 006_Orthogonal transformations - Orthogonal Matrices.mp4
. j. e2 H, ~9 w1 L! d │ 006_Orthogonal transformations - Orthogonal Matrices.srt& `$ }( H* I$ L/ Q, X8 {: @: O6 z
│ 007_Orthogonal matrices - Rotations and reflections.mp4* s7 S: z5 w) D9 a D# X
│ 007_Orthogonal matrices - Rotations and reflections.srt
' _) N" F( s( I! B: F* q │ 008_Parametrizing Rotations in 3D.mp4
" |* M0 V6 B8 `3 \( A$ ] │ 008_Parametrizing Rotations in 3D.srt9 T5 y; T$ V1 d; L1 j/ Q
│ 009_Euclidean, Affine and Projective Transformations.mp4
' a' s6 @, ^+ j8 F5 K( I% H4 ^ │ 009_Euclidean, Affine and Projective Transformations.srt
! C6 a8 }9 D: r7 a4 G │ 010_Dynamic Perspective - I [15 mins].mp4- G# l4 ?: }8 a( ^7 H3 z' O
│ 010_Dynamic Perspective - I [15 mins].srt% m8 m5 C5 a0 g& L; r6 v/ L
│ 011_Dynamic Perspective - II [25 mins].mp45 T$ x: F* ~& {& }; _/ w+ N
│ 011_Dynamic Perspective - II [25 mins].srt# z+ z. L2 D0 g
│ 012_Binocular Stereo I [23 mins].mp4: k4 J0 j) c: D! o( T
│ 012_Binocular Stereo I [23 mins].srt) F5 b" C( g1 P+ N
│ 013_Binocular Stereo II [17 mins].mp45 ^4 D6 ^6 Y" ?2 C* o3 H. X
│ 013_Binocular Stereo II [17 mins].srt5 b2 j' U @9 @- h S
│ 014_Binocular Stereo III [13 mins].mp4. o# i, j' T+ j# |$ J( E
│ 014_Binocular Stereo III [13 mins].srt; e9 }) ?1 n: |& c1 C& t0 b$ Q
│ 015_Binocular Stereo IV - The Essential Matrix [26 min].mp4/ ~5 S" o! h) j# y- @
│ 015_Binocular Stereo IV - The Essential Matrix [26 min].srt1 x8 ?% }+ d/ z7 m' m8 N/ \
│ 016_Radiometry.mp4$ u' V" d, M9 z
│ 016_Radiometry.srt
& T9 X: G% @3 {; e2 p+ w │ 017_Image processing.mp4- M8 i" P) {$ k0 X. Q) i" \
│ 017_Image processing.srt3 w6 G$ a9 _" i5 f) ?& Q+ L+ U) c, l
│ 018_Image Processing2.mp43 `* b/ a( N3 e1 ?* n* d$ {
│ 018_Image Processing2.srt" Q2 N( }$ R) C7 _7 A
│ 019_Orientation histograms [7 min].mp4- b3 s. G" H; {1 \
│ 019_Orientation histograms [7 min].srt
0 g6 s) r/ e, k6 r( ?. p' J% N7 a │ 020_Handwritten digit recognition - Introduction.mp4
+ {$ j- t# D! |1 }! r │ 020_Handwritten digit recognition - Introduction.srt) U$ l* L* \3 V- a' d
│ 021_Support Vector Machines.mp4
$ }- g4 b. ^1 b. X' B' n │ 021_Support Vector Machines.srt
' v2 D+ J5 `$ |6 j/ ] │ 022_Transformation Invariance and Histograms.mp45 Z+ i" D- w: Y B4 E2 c
│ 022_Transformation Invariance and Histograms.srt
( z& g. q- }& u- p9 ^ │ 023_Digit recognition using SVMs.mp4) C; L G% A) v9 A1 g
│ 023_Digit recognition using SVMs.srt3 O3 O T# D9 x$ U" J: F1 y
│ 024_Random forests.mp48 n7 i/ `7 P$ o: w6 l
│ 024_Random forests.srt
]! g* s/ m0 J/ [. g* f │ 025_Detection of 3D objects.mp4
* A; e( Q! N2 E( [3 _( @ │ 025_Detection of 3D objects.srt
6 L3 v' z1 I0 m' w+ | i, J N │ 026_Concluding Remarks.mp4$ i! ^5 } U" Y, s% {
│ 026_Concluding Remarks.srt
$ f% H' @! ]! h* } │ 下载说明.txt, J, S1 Z# u% J
│ 关注我们.png6 O; D4 [ O% ^4 d6 ~
│ 攻城狮论坛=网络技术+编程视频.url" e5 p6 V7 r! z* D' ?! L" I2 Z
│ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt. \+ |) T1 N$ O
│
* Z6 A& B4 l/ {4 S! F7 B ├─Practical Machine Learning
, z2 l. a0 i! R) P: k# F │ └─Practical Machine Learning
+ N. Y% u# q3 z9 g) _ │ │ 下载说明.txt5 y% Q3 k4 q5 u- q5 [
│ │ 关注我们.png0 ~, }( t3 I4 V% @
│ │ 攻城狮论坛=网络技术+编程视频.url0 H9 I1 o. H' n$ h' i/ f' _0 E6 @
│ │ 解压缩密码是方括号里的内容 [攻城狮论坛 bbs.vlan5.com].txt
8 H& Z! _; m$ H │ │ * \' P a/ V2 j
│ ├─Week1
! q8 H- l N' @ │ │ 001predictionMotivation.pdf( X/ T1 k: N5 W% m! o {
│ │ 002whatIsPrediction.pdf
5 i% w! @2 n: x5 R- d* P │ │ 003relativeImportance.pdf
# J2 a% I. s, |) G$ P │ │ 004inOutSampleErrors.pdf
) c8 v8 V; O4 q# T │ │ 005predictionStudyDesign.pdf8 \( Z, b2 Q: G( D( i: O& x
│ │ 006typesOfErrors.pdf: z) Q% Z% s5 p
│ │ 007receiverOperatingCharacteristic.pdf
( K' ?1 d# o3 z8 q │ │ 008crossValidation.pdf
8 ]2 D! u! s2 j% I" G9 t* s1 @ │ │ 009whatData.pdf B% z4 [# J F+ i9 ^
│ │ 1 - 1 - Prediction motivation (8-26).mp44 }+ u3 w# G3 t7 V( {' W* t' _
│ │ 1 - 1 - Prediction motivation (8-26).srt' P) G) L! i8 p1 \
│ │ 1 - 2 - What is prediction- (8-39).mp4
9 |7 \, o r$ O+ S │ │ 1 - 2 - What is prediction- (8-39).srt) n; x! t$ [; v* g# C+ b
│ │ 1 - 3 - Relative importance of steps (9-45).mp49 O6 U& J# Q1 R
│ │ 1 - 3 - Relative importance of steps (9-45).srt- G) L8 K: U/ \9 {0 S; D* D- V8 }
│ │ 1 - 4 - In and out of sample errors (6-57).mp4% ^' ?5 p) |. Q! [5 }0 h6 e: Y
│ │ 1 - 4 - In and out of sample errors (6-57).srt
2 r6 N. ?. z# V+ y* m │ │ 1 - 5 - Prediction study design (9-05).mp4
7 B* k. R, E5 _. R │ │ 1 - 5 - Prediction study design (9-05).srt# T/ L3 ]; X1 m
│ │ 1 - 6 - Getting Data Overview (1-34).mp4
7 f0 u* i' ^" |) }3 x, n! \+ n │ │ 1 - 6 - Types of errors (10-35).mp4- C6 Y: `* ^2 ?* s; P _% S
│ │ 1 - 6 - Types of errors (10-35).srt
1 ]- w; @1 g1 r- F- ^ │ │ 1 - 7 - Receiver Operating Characteristic (5-03).mp42 |. m7 m+ o+ W2 y) ]. n4 B9 z' `+ H! `
│ │ 1 - 7 - Receiver Operating Characteristic (5-03).srt4 m3 {+ o7 ?% `, p9 U) N6 ]
│ │ 1 - 8 - Cross validation (8-20).mp4
8 G; ^( w) F- w: ` │ │ 1 - 8 - Cross validation (8-20).srt$ l# K, M: T5 {. }, y
│ │ 1 - 9 - What data should you use- (6-01).mp4" n. O+ z/ j1 W9 n4 F, w
│ │ 1 - 9 - What data should you use- (6-01).srt
- a: b+ k* E8 U! ~/ J/ H Z │ │ + J5 k( G* D3 v2 j! M
│ ├─Week2/ q; v4 V+ {4 d
│ │ 010caretPackage.pdf2 t7 q' K$ U$ Y) J: J
│ │ 011dataSlicing.pdf
$ V- N i+ T) y │ │ 012trainOptions.pdf
7 X, N" K& r( | │ │ 013plottingPredictors.pdf' P! s0 _8 b) d, W7 T. a# o
│ │ 014basicPreprocessing.pdf
% D/ a! x r) P │ │ 015covariateCreation.pdf0 y0 Y4 O' d( k* y( f0 S
│ │ 016preProcessingPCA.pdf; x7 M% G9 U8 }7 W4 D2 y& z$ `
│ │ 017predictingWithRegression.pdf
1 t2 _8 y6 _% C' A$ a8 `. o5 k │ │ 018predictingWithRegressionMC.pdf6 D& N* R8 \% P; ]% L& a
│ │ 2 - 1 - Caret package (6-16).mp4: L' Q" K' Y# a1 q- @! H& _9 e3 F
│ │ 2 - 1 - Caret package (6-16).srt
. F4 X' n2 C U │ │ 2 - 1 - Caret package (6-16).txt
6 _& o# r- g5 A4 {3 a! e │ │ 2 - 2 - Data slicing (5-40).mp4
- m$ e" z! @& @% E. k. K2 K │ │ 2 - 2 - Data slicing (5-40).srt
. D7 k1 {4 y" {; M7 ` │ │ 2 - 2 - Data slicing (5-40).txt
2 V$ p. ]2 f7 u9 i* f/ b' q9 G │ │ 2 - 3 - Training options (7-15).mp4
' G3 O& H7 \( `0 X3 E+ ? │ │ 2 - 3 - Training options (7-15).srt
$ p: [! Y8 t" d │ │ 2 - 3 - Training options (7-15).txt
0 ] g( ?2 g2 i% c │ │ 2 - 4 - Plotting predictors (10-39).mp4
2 M; p) w1 v* [5 K& O │ │ 2 - 4 - Plotting predictors (10-39).srt7 D# f2 }5 i9 i' X. K( z- q
│ │ 2 - 4 - Plotting predictors (10-39).txt& v' T9 S$ N! U8 H; s4 v1 O7 ]
│ │ 2 - 5 - Basic preprocessing (10-52).mp4
" s: i- H0 ?- T: h4 n │ │ 2 - 5 - Basic preprocessing (10-52).srt* b' L# s6 T& v1 i- }
│ │ 2 - 5 - Basic preprocessing (10-52).txt
; s' r R6 F, g( N# ]* A │ │ 2 - 6 - Covariate creation (17-31).mp4
9 L. k: H8 m1 ?! L2 C$ B │ │ 2 - 6 - Covariate creation (17-31).srt
- [! T4 L, Z# D: {' L │ │ 2 - 6 - Covariate creation (17-31).txt- @& D; {$ J# Z) \5 Y/ M
│ │ 2 - 7 - Preprocessing with principal components analysis (14-07).mp4
7 @% q2 L3 S# ~4 B" y- C │ │ 2 - 7 - Preprocessing with principal components analysis (14-07).srt
+ A4 n! E# e6 I5 v. C │ │ 2 - 7 - Preprocessing with principal components analysis (14-07).txt* \0 ~& Z* F; q% _! v
│ │ 2 - 8 - Predicting with Regression (12-22).mp4
& W9 B: m6 B* }) R7 Q) h │ │ 2 - 8 - Predicting with Regression (12-22).srt
. F( f! n$ p, p+ Q │ │ 2 - 8 - Predicting with Regression (12-22).txt
e4 s; f7 t6 ]6 d! t9 Q$ u8 S │ │ 2 - 9 - Predicting with Regression Multiple Covariates (11-12).mp44 S3 J2 b5 T3 k a0 p4 j
│ │ 2 - 9 - Predicting with Regression Multiple Covariates (11-12).srt0 u; r8 ]$ o3 h$ u! e
│ │ 2 - 9 - Predicting with Regression Multiple Covariates (11-12).txt, q. e( m" K, F" B. `6 f/ D
│ │
2 I6 g1 x: j x! h( ? │ ├─Week3
& |$ O! H4 Y c& \ │ │ 019predictingWithTrees.pdf
) p4 I& L5 w( p/ z │ │ 020bagging.pdf
4 N7 z( h0 b- C8 t+ Q0 V │ │ 021randomForests.pdf
" P* t. O# z# J& } │ │ 022boosting.pdf0 G6 r3 b, [0 x3 L' G7 R+ l( P ^, }
│ │ 023modelBasedPrediction.pdf: L9 S+ Q6 d1 G% B8 A, X9 M
│ │ 3 - 1 - Predicting with trees (12-51).mp4) @! X1 M; A' D, J% B6 K3 D1 y
│ │ 3 - 1 - Predicting with trees (12-51).srt" Z4 M' D; u# b% K. W
│ │ 3 - 1 - Predicting with trees (12-51).txt
7 e/ g# j9 l4 ]) I, Q+ x+ { │ │ 3 - 2 - Bagging (9-13).mp4" p& D2 m0 Z) h5 q0 t
│ │ 3 - 2 - Bagging (9-13).srt$ C8 n* l& J/ l) E# U
│ │ 3 - 2 - Bagging (9-13).txt
# H' D# L9 Z1 r% I9 s │ │ 3 - 3 - Random Forests (6-49).mp4
1 y9 @9 |* V% S* J# V' Y │ │ 3 - 3 - Random Forests (6-49).srt2 _4 W0 `, |' O/ F3 ?, t
│ │ 3 - 3 - Random Forests (6-49).txt
" ^9 h7 [0 u/ w( n4 W- [# c* Y │ │ 3 - 4 - Boosting (7-08).mp4
v/ p! Q* J, f$ e6 ^6 k5 R │ │ 3 - 4 - Boosting (7-08).srt
. I* B, `% H; ?+ f& ]1 {, u │ │ 3 - 4 - Boosting (7-08).txt
& |/ |0 D: r+ N4 G2 e/ P │ │ 3 - 5 - Model Based Prediction (11-39).mp4
! w9 T F* K6 m. J' F │ │ 3 - 5 - Model Based Prediction (11-39).srt
! C5 Q: G7 g9 D9 @& G' r │ │ 3 - 5 - Model Based Prediction (11-39).txt
5 M/ M% N' X( a" Z0 a A │ │ 0 o. t4 }' ^3 I1 W' Q7 p5 Q
│ └─Week48 L" n) j8 Y2 P6 s0 K9 D8 }; w/ {2 P0 T$ y
│ 024regularizedRegression.pdf8 G. e/ ?3 w5 I; e
│ 025combiningPredictors.pdf5 W4 m# F7 M- \" N) G9 e" v/ l
│ 026unsupervisedPrediction.pdf3 @8 q8 v& c. `, D
│ 027forecasting.pdf
8 ?! U7 j9 |7 z │ 4 - 1 - Regularized regression (13-20).mp4
' C [6 x3 d% E2 Z# B5 o0 P7 s │ 4 - 1 - Regularized regression (13-20).srt
( R0 F/ [3 l5 h) B' l( s* s │ 4 - 1 - Regularized regression (13-20).txt% Z4 e- \1 ^1 Q
│ 4 - 2 - Combining predictors (7-11).mp4
( b) K5 r4 v# Y6 P4 B0 s │ 4 - 2 - Combining predictors (7-11).srt. \& {9 Y* ]) j/ ^5 q8 @) }
│ 4 - 2 - Combining predictors (7-11).txt! }: r- k+ s3 ~' A4 p
│ 4 - 3 - Forecasting.mp4: V3 P/ v$ N4 Y# F: T( d4 J. V9 m
│ 4 - 3 - Forecasting.srt
6 ]! s. O9 M4 b$ ^, t │ 4 - 3 - Forecasting.txt
8 w. h. }' e5 _% X1 B │ 4 - 4 - Unsupervised Prediction (4-24).mp4" y3 p4 c% Q: A; O9 d8 Y
│ 4 - 4 - Unsupervised Prediction (4-24).srt
2 X t; q) O3 u( |4 J2 l% p │ 4 - 4 - Unsupervised Prediction (4-24).txt
2 B0 i u1 S7 a6 G# Q" ], |2 s │
" h) ?# L& J! i- s/ p- U- p ├─Sapiro - Image and video processing2 t" g0 @# N, \& C' ^1 Q
│ 01.pdf
' j' h- A7 t. \# r │ 02.pdf- T( x# @/ c, w9 o# i9 G# \. J
│ 03.pdf8 d* p7 o- x2 K; f% _* Z
│ 04.pdf8 x @* w# k) i1 s' s( E7 k
│ 05.pdf
% }* Q0 S2 @3 E) w │ 06.pdf6 [/ b3 {+ {( q# a6 G
│ 07.pdf
, g1 P4 Z4 |# r( ?9 t2 c [2 @ z5 u │ 08.pdf- S1 @7 L+ y/ _9 v% g6 ?# c$ P
│ 10 - 1 - 1 - Introduction to Medical Imaging - Duration 0703.mp4, S. B- u, c8 o: }5 s! K g
│ 10 - 1 - 1 - Introduction to Medical Imaging - Duration 0703.srt5 F5 C2 \& T1 T" G- Z. {
│ 10 - 1 - 1 - Introduction to Medical Imaging - Duration 0703.txt) f9 i0 ^7 Z% e
│ 10 - 2 - 2 - Image Processing and HIV (Part I) - Duration 2351 - Optional breaks at 1237 and 1839.mp4) v' s0 ^; I( H. U
│ 10 - 2 - 2 - Image Processing and HIV (Part I) - Duration 2351 - Optional breaks at 1237 and 1839.srt! P' w* j7 }, { O$ K
│ 10 - 2 - 2 - Image Processing and HIV (Part I) - Duration 2351 - Optional breaks at 1237 and 1839.txt) K4 P% k4 @4 g. g. ]
│ 10 - 3 - 2 - Image Processing and HIV (Part II) - Duration 1630.mp4' r! }8 K. @" R. R3 P, p
│ 10 - 3 - 2 - Image Processing and HIV (Part II) - Duration 1630.srt
7 x+ ` x3 |; }& T% [0 d; X( g% F │ 10 - 3 - 2 - Image Processing and HIV (Part II) - Duration 1630.txt
3 T8 K/ K" O7 O │ 10 - 4 - 3 - Brain Imaging Diffusion Imaging Deep Brain Stimulation - Duration 2628.mp4
1 w2 l2 o9 M+ j m- j4 y │ 10 - 4 - 3 - Brain Imaging Diffusion Imaging Deep Brain Stimulation - Duration 2628.srt! J V/ O1 @" i
│ 10 - 4 - 3 - Brain Imaging Diffusion Imaging Deep Brain Stimulation - Duration 2628.txt: n* A7 q+ j3 v y
│ 10 - 5 - 4 - Thanks.mp4' k7 M8 `# B9 ]) @, @( x
│ 10 - 5 - 4 - Thanks.srt
4 g$ }- Q/ T9 s" J │ 10 - 5 - 4 - Thanks.txt* f; k, U0 ]+ E6 s; ?$ x4 _: ]
│ 2 - 1 - 0 - Welcome and Start Here.mp4
4 J$ J1 N2 F2 O& r0 I% K │ 2 - 1 - 0 - Welcome and Start Here.srt# K/ g' M- D5 O- b+ r" E% W: E8 A
│ 2 - 1 - 0 - Welcome and Start Here.txt
9 j( V* n* J* M( ? │ 2 - 2 - 1 - What is image and video processing (part 1) - Duration 1049.mp4
5 i7 h3 b% A! s │ 2 - 2 - 1 - What is image and video processing (part 1) - Duration 1049.srt; }/ ~/ p9 @3 i3 a+ Q
│ 2 - 3 - 1 - What is image and video processing (part 2) - Duration 1040.mp4
# m2 b4 a/ ^2 L8 o │ 2 - 3 - 1 - What is image and video processing (part 2) - Duration 1040.srt
, m3 I' I3 u+ X+ B. X, z7 k; K% q/ C │ 2 - 3 - 1 - What is image and video processing (part 2) - Duration 1040.txt7 n# E& T- E: S f* m6 Z
│ 2 - 4 - 2 - Course logistics - Duration 0242.mp41 M5 z+ W& C4 I; a' f" T& _& E' ~. m
│ 2 - 4 - 2 - Course logistics - Duration 0242.srt. q4 d0 q( I9 f6 j
│ 2 - 4 - 2 - Course logistics - Duration 0242.txt5 ^6 L: l% S2 |: |* \% {
│ 2 - 5 - 3 - Images are everywhere - Duration 0631.mp4
1 ?: x- T( A. c* ` S t │ 2 - 5 - 3 - Images are everywhere - Duration 0631.srt7 B4 X1 I; f+ b i# l$ l5 D$ \* L
│ 2 - 5 - 3 - Images are everywhere - Duration 0631.txt% R* o5 l& o! |8 K( N9 _! V3 y
│ 2 - 6 - 4 - Human visual system - Duration 1710.mp4: Y+ b3 l0 j! G3 e7 r
│ 2 - 6 - 4 - Human visual system - Duration 1710.srt8 {7 A; Q# U7 {+ h, ]
│ 2 - 6 - 4 - Human visual system - Duration 1710.txt
, [# s% `* g4 n, L# n │ 2 - 7 - 5 - Image formation - Sampling Quantization - Duration 2817.mp4
! Y! _2 B" G" F- T y& G │ 2 - 7 - 5 - Image formation - Sampling Quantization - Duration 2817.srt
d+ W+ _5 W( s( H │ 2 - 7 - 5 - Image formation - Sampling Quantization - Duration 2817.txt
! D! J+ D/ k9 u0 q4 b/ K+ o- H1 } │ 2 - 8 - 6 - Simple image operations - Duration 1705.mp4
0 Z. G6 R5 ~; c& N1 h: L │ 2 - 8 - 6 - Simple image operations - Duration 1705.srt! A- J$ I9 g0 L
│ 2 - 8 - 6 - Simple image operations - Duration 1705.txt0 S9 P4 e" T0 y3 ? c: X
│ 3 - 1 - 1 - The why and how of compression - Duration 1416.mp44 E! n. M" G7 D4 r: ?- {% z s* `
│ 3 - 1 - 1 - The why and how of compression - Duration 1416.srt
$ ]3 d6 o1 ?7 R9 U │ 3 - 1 - 1 - The why and how of compression - Duration 1416.txt. @% _0 ^& n0 V( w: r6 g
│ 3 - 2 - 2 - Huffman coding - Duration 2011 - Optional break at 0653.mp4
1 a( v( K8 g. j; t: y+ t4 p" G │ 3 - 2 - 2 - Huffman coding - Duration 2011 - Optional break at 0653.srt
: X& ]; O8 z1 d: A0 Y$ Q( o p' _ │ 3 - 2 - 2 - Huffman coding - Duration 2011 - Optional break at 0653.txt
) h: C: F g2 W5 F- l: h& P │ 3 - 3 - 3 - JPEGs 8x8 blocks - Duration 0537.mp4
% M( Y( m$ O6 g& V │ 3 - 3 - 3 - JPEGs 8x8 blocks - Duration 0537.srt
+ |' z3 X# G0 ^ │ 3 - 3 - 3 - JPEGs 8x8 blocks - Duration 0537.txt$ R3 }% C* m' q/ I: z
│ 3 - 4 - 4 - The Discrete Cosine Transform (DCT) - Duration 2532 - Optional break at 1213.mp4
5 w3 m* {, Y$ s, n: v( m7 M │ 3 - 4 - 4 - The Discrete Cosine Transform (DCT) - Duration 2532 - Optional break at 1213.srt
3 T5 f" A3 U1 y4 u0 b1 L$ C" T │ 3 - 4 - 4 - The Discrete Cosine Transform (DCT) - Duration 2532 - Optional break at 1213.txt4 T0 e4 K' X0 L% B2 Q+ [+ t2 ]
│ 3 - 5 - 5 - Quantization - Duration 2402 - Optional breaks at 0848 and 1718.mp43 K; S2 N) A; p8 d
│ 3 - 5 - 5 - Quantization - Duration 2402 - Optional breaks at 0848 and 1718.srt+ Y$ [; u$ L/ n, p* m% v
│ 3 - 5 - 5 - Quantization - Duration 2402 - Optional breaks at 0848 and 1718.txt- M) m% p- V% q- A) c3 u5 H- r- a
│ 3 - 6 - 6 - JPEG_LS and MPEG - Duration 1932 - Optional break at 1345.mp4
& I3 l+ C( \/ f' m │ 3 - 6 - 6 - JPEG_LS and MPEG - Duration 1932 - Optional break at 1345.srt: D/ o4 y, j/ w+ v7 q7 X
│ 3 - 6 - 6 - JPEG_LS and MPEG - Duration 1932 - Optional break at 1345.txt
6 \( Q' B2 h+ f1 q# T) w! U8 ` │ 3 - 7 - 7 - Bonus Run-length compression - Duration 0429.mp4( z9 e7 O$ g# ?- g
│ 3 - 7 - 7 - Bonus Run-length compression - Duration 0429.srt$ ?; g) S7 X, u$ p
│ 3 - 7 - 7 - Bonus Run-length compression - Duration 0429.txt! K" a' t4 C1 d, a/ _! w* S9 Z
│ 4 - 1 - 1 - Introduction to image enhancement - Duration 1911 - Optional break at 0833.mp4
) e9 u3 y7 f/ e4 Z4 O │ 4 - 1 - 1 - Introduction to image enhancement - Duration 1911 - Optional break at 0833.srt7 S. M' `4 o% q {" q
│ 4 - 1 - 1 - Introduction to image enhancement - Duration 1911 - Optional break at 0833.txt
+ G) S0 S0 m. A, \. g4 C; Y! P │ 4 - 10 - 10 - Demo - Median filter - Duration 0131.mp4
/ `+ p$ \6 J. N# `) A+ h& n │ 4 - 10 - 10 - Demo - Median filter - Duration 0131.srt
0 Y7 K1 q+ x8 ^ │ 4 - 10 - 10 - Demo - Median filter - Duration 0131.txt* C8 _& ?" z! _! ]7 v: G
│ 4 - 11 - 11 - Derivatives Laplacian Unsharp masking - Duration 1424 - Optional breaks at 0521 and 1133.mp4. Q, W8 }9 p# U6 b3 L3 m
│ 4 - 11 - 11 - Derivatives Laplacian Unsharp masking - Duration 1424 - Optional breaks at 0521 and 1133.srt( t. a( ?: r: ?! G5 w+ E- u, J
│ 4 - 11 - 11 - Derivatives Laplacian Unsharp masking - Duration 1424 - Optional breaks at 0521 and 1133.txt2 z) ?5 U/ {# a. k5 b
│ 4 - 12 - 12 - Demo - Unsharp masking - Duration 0310.mp4
- C* o) U9 M) c+ k2 s7 G. d │ 4 - 12 - 12 - Demo - Unsharp masking - Duration 0310.srt) n: a% c7 y4 m) a) Q6 [1 h
│ 4 - 12 - 12 - Demo - Unsharp masking - Duration 0310.txt
( @7 C/ P# O$ k. N% r │ 4 - 13 - 13 - Gradients of scalar and vector images - Duration 0557.mp4
2 h9 `. J! [' S# R │ 4 - 13 - 13 - Gradients of scalar and vector images - Duration 0557.srt2 W# u/ a% A4 m) \
│ 4 - 13 - 13 - Gradients of scalar and vector images - Duration 0557.txt9 L: w4 x& g ]
│ 4 - 14 - 14 - Concluding remarks - Duration 0112.mp46 a8 Q; Q) F3 U8 S" n7 h7 _4 J& ~
│ 4 - 14 - 14 - Concluding remarks - Duration 0112.srt
1 o* ], n+ M! R8 @! ?: P$ P8 N │ 4 - 14 - 14 - Concluding remarks - Duration 0112.txt
$ ?' e% Z: `" f6 u, f │ 4 - 2 - 2 - Demo - Enhancement Histogram modification - Duration 0353.mp4; s( N/ A9 i) P6 e/ g# A
│ 4 - 2 - 2 - Demo - Enhancement Histogram modification - Duration 0353.srt* i" A6 U' t) g
│ 4 - 2 - 2 - Demo - Enhancement Histogram modification - Duration 0353.txt
4 I1 z" }8 T' w3 G0 F │ 4 - 3 - 3 - Histogram equalization - Duration 1956 - Optional breaks at 0440 and 1130.mp4
* f, p5 A5 D6 ]7 O& w& g9 F1 j │ 4 - 3 - 3 - Histogram equalization - Duration 1956 - Optional breaks at 0440 and 1130.srt
! Y! A3 `. P1 C' p: H3 Q { { │ 4 - 3 - 3 - Histogram equalization - Duration 1956 - Optional breaks at 0440 and 1130.txt7 y* R5 b+ r! _6 Q: x( [0 `
│ 4 - 4 - 4 - Histogram matching - Duration 0831.mp42 S& K+ P3 \+ t. N0 i! U2 `5 t
│ 4 - 4 - 4 - Histogram matching - Duration 0831.srt$ c2 `' b/ j t9 Z0 v
│ 4 - 4 - 4 - Histogram matching - Duration 0831.txt- u% I% }/ }- E8 n# q$ N
│ 4 - 5 - 5 - Introduction to local neighborhood operations - Duration 0646.mp4
8 f/ l& {7 _ p. V │ 4 - 5 - 5 - Introduction to local neighborhood operations - Duration 0646.srt1 I, }$ ? F5 p/ W5 Z1 ]) K; C
│ 4 - 5 - 5 - Introduction to local neighborhood operations - Duration 0646.txt; @; h. H! F$ F
│ 4 - 6 - 6 - Mathematical properties of averaging - Duration 1100.mp4, [& |. T. p$ U* R+ J5 D
│ 4 - 6 - 6 - Mathematical properties of averaging - Duration 1100.srt
% |) w- F! I( D │ 4 - 6 - 6 - Mathematical properties of averaging - Duration 1100.txt
2 m; }& y# N5 t8 `7 M5 k5 d │ 4 - 7 - 7 - Non-Local means - Duration 0727.mp4+ o2 C+ c( o! G+ n) D, t. V5 {2 \! s
│ 4 - 7 - 7 - Non-Local means - Duration 0727.srt9 r4 [# t. e, T' Y8 d! {
│ 4 - 7 - 7 - Non-Local means - Duration 0727.txt
1 H' t2 B4 Q! b; ^. ^ │ 4 - 8 - 8 - IPOL Demo - Non-Local means - Duration 0338.mp4& W# X3 B& @! |' v4 f8 M. ~
│ 4 - 8 - 8 - IPOL Demo - Non-Local means - Duration 0338.srt/ o6 X3 \% C- W2 E0 d* |
│ 4 - 8 - 8 - IPOL Demo - Non-Local means - Duration 0338.txt' ~3 Z4 E9 b! r1 G7 t
│ 4 - 9 - 9 - Median filter - Duration 0720.mp4+ R8 y) ]+ L2 C7 G1 B/ i9 B
│ 4 - 9 - 9 - Median filter - Duration 0720.srt9 Z% F/ I) K" C: Z/ ]0 K
│ 4 - 9 - 9 - Median filter - Duration 0720.txt
8 r, |- I: G) h& ] │ 5 - 1 - 1 - What is image restoration - Duration 0749.mp4( z2 H7 i% n1 q' D- {" I
│ 5 - 1 - 1 - What is image restoration - Duration 0749.srt0 B$ j8 y% i: d# x
│ 5 - 1 - 1 - What is image restoration - Duration 0749.txt
) Z" W9 }# r4 U y │ 5 - 2 - 2 - Noise types - Duration 1243.mp4
8 o6 C! _) v7 [% } │ 5 - 2 - 2 - Noise types - Duration 1243.srt+ G, B! C7 W/ y& W. ~; e
│ 5 - 2 - 2 - Noise types - Duration 1243.txt/ F. m# T% O1 B( B) o
│ 5 - 3 - 3 - Demo - Types of noise - Duration 0303.mp4
" a. A# u, j6 X/ a( V* H5 o. l │ 5 - 3 - 3 - Demo - Types of noise - Duration 0303.srt
4 d6 y- W* q5 D* J. C │ 5 - 3 - 3 - Demo - Types of noise - Duration 0303.txt) ~7 B( @2 j d# S4 U& d
│ 5 - 4 - 4 - Noise and histograms - Duration 0452.mp4
! t) |8 Z% d/ m: N$ ~4 G: {" X │ 5 - 4 - 4 - Noise and histograms - Duration 0452.srt/ U4 e; \: p( E5 @% n! j4 r
│ 5 - 4 - 4 - Noise and histograms - Duration 0452.txt# o% d5 u' q. \
│ 5 - 5 - 5 - Estimating noise - Duration 1041 - Optional break at 0503.mp4
7 |. M$ n: R4 X' |3 c: O │ 5 - 5 - 5 - Estimating noise - Duration 1041 - Optional break at 0503.srt9 @$ f1 ?8 I. `$ C4 D7 M
│ 5 - 5 - 5 - Estimating noise - Duration 1041 - Optional break at 0503.txt0 o9 B+ R! H& a: k* W
│ 5 - 6 - 6 - Degradation Function - Duration 1140.mp45 w( w1 `3 q# [
│ 5 - 6 - 6 - Degradation Function - Duration 1140.srt- }4 G* P3 V9 C l% O- x
│ 5 - 6 - 6 - Degradation Function - Duration 1140.txt! ?* i% x$ c9 e+ T3 r/ A7 r3 g) z, B
│ 5 - 7 - 7 - Wiener filtering - Duration 1234 - Optional break at 0654.mp4( Y* |8 Q2 D5 n: @( \
│ 5 - 7 - 7 - Wiener filtering - Duration 1234 - Optional break at 0654.srt
. ~7 O2 F1 D; ~3 e, ?% r │ 5 - 7 - 7 - Wiener filtering - Duration 1234 - Optional break at 0654.txt
5 l2 I5 L$ N) F- h8 Y │ 5 - 8 - 8 - Demo - Wiener and Box filters - Duration 0319.mp47 K/ a% ~0 W' K& n
│ 5 - 8 - 8 - Demo - Wiener and Box filters - Duration 0319.srt
( I% M3 M+ L, B) } │ 5 - 8 - 8 - Demo - Wiener and Box filters - Duration 0319.txt
6 k0 ]1 I' F9 t9 b, T │ 5 - 9 - 9 - Concluding remarks - Duration 0033.mp4
2 W3 q" I e! U( r% s# `! f& x. u │ 5 - 9 - 9 - Concluding remarks - Duration 0033.srt
4 D; L/ N. m) J& m% c │ 5 - 9 - 9 - Concluding remarks - Duration 0033.txt
+ E: [/ ]* ~# m5 \" e9 _. i │ 6 - 1 - 1 - Introduction to Segmentation - Duration 0417.mp4/ d4 g O; K9 W3 {
│ 6 - 1 - 1 - Introduction to Segmentation - Duration 0417.srt
4 `- g5 B/ O2 F! O │ 6 - 1 - 1 - Introduction to Segmentation - Duration 0417.txt. i; x$ m& _4 O1 W. o: ?( m' C) X
│ 6 - 10 - 10 - Active Contours - Introduction with ipol.im and Photoshop Demos - Duration 0558.mp4( g* L# P9 P7 p4 C( }
│ 6 - 10 - 10 - Active Contours - Introduction with ipol.im and Photoshop Demos - Duration 0558.srt1 u: s5 b# F: R" C) e' ~# q4 @
│ 6 - 10 - 10 - Active Contours - Introduction with ipol.im and Photoshop Demos - Duration 0558.txt
8 r. U, ^* }. Q; b1 w) h+ r │ 6 - 11 - 11 - Behind the Scenes of Adobes Roto Brush - Duration 3129 - Optional breaks at 2030 and 2726.mp4
, R, t3 E& D8 ~# Y3 g/ Z4 b │ 6 - 11 - 11 - Behind the Scenes of Adobes Roto Brush - Duration 3129 - Optional breaks at 2030 and 2726.srt' E( z, J% o$ ]8 t' ?
│ 6 - 11 - 11 - Behind the Scenes of Adobes Roto Brush - Duration 3129 - Optional breaks at 2030 and 2726.txt
) Y1 {+ o) W! O6 Z( L; A/ J │ 6 - 12 - 12 - End of the Week - Duration 0021.mp48 x% T- {$ h$ ~" V
│ 6 - 12 - 12 - End of the Week - Duration 0021.srt
6 S4 a r0 [9 O- E* x2 p │ 6 - 12 - 12 - End of the Week - Duration 0021.txt, ?7 H/ Q! u" G' R) p/ A/ A: p
│ 6 - 2 - 2 - On Edges and Regions - Duration 0517.mp4$ y5 I/ P+ E6 n
│ 6 - 2 - 2 - On Edges and Regions - Duration 0517.srt3 e7 C% Z5 H/ M/ x+ T
│ 6 - 2 - 2 - On Edges and Regions - Duration 0517.txt
8 h; K1 j! h n( N. l3 a5 \% b │ 6 - 3 - 3 - Hough Transform with Matlab Demo - Duration 2059.mp4- h" `. t1 Y1 Y# J7 G( y
│ 6 - 3 - 3 - Hough Transform with Matlab Demo - Duration 2059.srt+ t, ~4 L( f2 c' M# k! x, \
│ 6 - 3 - 3 - Hough Transform with Matlab Demo - Duration 2059.txt
- s; i9 Q& a- N- z1 H- s) r8 T │ 6 - 4 - 4 - Line Segment Detector with Demo - Duration 0320.mp4- T% y8 u O c j# o
│ 6 - 4 - 4 - Line Segment Detector with Demo - Duration 0320.srt
. J1 y4 q. X" F; I │ 6 - 4 - 4 - Line Segment Detector with Demo - Duration 0320.txt
$ m+ q2 N, n5 y, V3 C │ 6 - 5 - 5 - Otsus Segmentation with Demo - Duration 1425.mp4
3 k' \& b- ~" U! W, ~' ~ │ 6 - 5 - 5 - Otsus Segmentation with Demo - Duration 1425.srt7 o6 ^! j7 X2 u3 h5 R
│ 6 - 5 - 5 - Otsus Segmentation with Demo - Duration 1425.txt5 [4 V J1 a( t- `8 @* r
│ 6 - 6 - 6 - Congratulations - Duration 0017.mp4
Y, ~- e( U5 S1 m# c │ 6 - 6 - 6 - Congratulations - Duration 0017.srt
! J! u1 [0 k5 W' U8 f) | │ 6 - 6 - 6 - Congratulations - Duration 0017.txt
5 k3 m7 e4 v V7 c) d │ 6 - 7 - 7 - Interactive Image Segmentation - Duration 2113.mp4' d; Q3 [3 L9 A( b2 I4 U* R
│ 6 - 7 - 7 - Interactive Image Segmentation - Duration 2113.srt5 a8 f. W. P% r3 U/ W
│ 6 - 7 - 7 - Interactive Image Segmentation - Duration 2113.txt) C4 O( y' @9 k
│ 6 - 8 - 8 - Graph Cuts and Ms Office - Duration 0934.mp4
0 j" N9 ^& C0 S( K │ 6 - 8 - 8 - Graph Cuts and Ms Office - Duration 0934.srt
) a- I, t) h( _( D$ R& q% M │ 6 - 8 - 8 - Graph Cuts and Ms Office - Duration 0934.txt6 m$ ?/ {! N; \/ X' ~8 N1 m
│ 6 - 9 - 9 - Mumford-Shah - Duration 0550.mp4
- J" |. r$ d( E: |0 O0 T( g │ 6 - 9 - 9 - Mumford-Shah - Duration 0550.srt
' q6 N/ k' a9 `0 t" [" v6 g │ 6 - 9 - 9 - Mumford-Shah - Duration 0550.txt
! ?7 ^: {8 r& q4 r' X; |" S. `( _ │ 7 - 1 - 1 - Introduction to PDEs in Image and Video Processing - Duration 1022.mp4
" @) |% {4 Y1 q3 N/ G3 \ │ 7 - 1 - 1 - Introduction to PDEs in Image and Video Processing - Duration 1022.srt% i f V/ I$ j/ _7 K8 @- R" h
│ 7 - 1 - 1 - Introduction to PDEs in Image and Video Processing - Duration 1022.txt
, W: S8 ^7 G% E$ a' E% K' l │ 7 - 2 - 2 - Planar Differential Geometry - Duration 3833 - Optional breaks at 1246 2103 and 2941.mp4/ O9 {/ F/ D9 T) E( a% _; K- Z
│ 7 - 2 - 2 - Planar Differential Geometry - Duration 3833 - Optional breaks at 1246 2103 and 2941.srt
& L' F* X( G5 Q │ 7 - 2 - 2 - Planar Differential Geometry - Duration 3833 - Optional breaks at 1246 2103 and 2941.txt m2 ^0 r: k8 P3 Q% r, Z r; [# i7 y
│ 7 - 3 - 3 - Surface Differential Geometry - Duration 1143.mp44 V- ?. ^" T% q7 K
│ 7 - 3 - 3 - Surface Differential Geometry - Duration 1143.srt
# H3 g; Q8 ?) b, E7 ~. a │ 7 - 3 - 3 - Surface Differential Geometry - Duration 1143.txt
( [: f {% i/ y1 u- K │ 7 - 4 - 4 - Curve Evolution - Duration 3110 - Optional breaks at 0850 1925 and 2422.mp47 g2 Y6 ^9 I% D' ]6 a+ C
│ 7 - 4 - 4 - Curve Evolution - Duration 3110 - Optional breaks at 0850 1925 and 2422.srt* h4 U+ ?( q2 V, X. S- d2 o* J
│ 7 - 4 - 4 - Curve Evolution - Duration 3110 - Optional breaks at 0850 1925 and 2422.txt) t; h/ h* G3 W+ c5 A1 \
│ 7 - 5 - 5 - Level Sets and Curve Evolution - Duration 2534 - Optional break at 1430.mp4" W2 f: I4 z2 ]
│ 7 - 5 - 5 - Level Sets and Curve Evolution - Duration 2534 - Optional break at 1430.srt. @$ z1 H- j: U: R9 V( n
│ 7 - 5 - 5 - Level Sets and Curve Evolution - Duration 2534 - Optional break at 1430.txt3 p- f# d- ]) t2 P
│ 7 - 6 - 6 - Calculus of Variations - Duration 1403 - Optional break at 0623.mp4
7 o+ r& F# k" E' l0 b* z │ 7 - 6 - 6 - Calculus of Variations - Duration 1403 - Optional break at 0623.srt' w- i( v9 r3 R3 P v* q t4 T
│ 7 - 6 - 6 - Calculus of Variations - Duration 1403 - Optional break at 0623.txt
# y! y6 i7 `( P │ 7 - 7 - 7 - Anisotropic Diffusion - Duration 1117.mp4
0 S! P2 |' ~1 W+ ` │ 7 - 7 - 7 - Anisotropic Diffusion - Duration 1117.srt
3 H: R+ R' W4 B+ W │ 7 - 7 - 7 - Anisotropic Diffusion - Duration 1117.txt$ F D3 V( V1 |; |( ]
│ 7 - 8 - 8 - Active Contours - Duration 1657 - Optional break at 0623.mp4
7 j* h) [6 d! Y; Z! e1 _7 M$ U4 A │ 7 - 8 - 8 - Active Contours - Duration 1657 - Optional break at 0623.srt! k: \1 C) z9 ~; X
│ 7 - 8 - 8 - Active Contours - Duration 1657 - Optional break at 0623.txt' h1 u O. x# b3 t5 I5 _
│ 7 - 9 - 9 - Bonus Cool Contrast Enhancement via PDEs - Duration 0832.mp4
5 F" ^- a c x9 v, S$ { │ 7 - 9 - 9 - Bonus Cool Contrast Enhancement via PDEs - Duration 0832.srt
# J2 J! U5 x. p │ 7 - 9 - 9 - Bonus Cool Contrast Enhancement via PDEs - Duration 0832.txt" `$ X% u; ` C! X+ M* E. P8 ^$ O" X, W+ J
│ 8 - 1 - 1 - Introduction to Image Inpainting - Duration 0816.mp4
6 m- w9 u6 h* P- t% \, V- T8 F/ @6 G │ 8 - 1 - 1 - Introduction to Image Inpainting - Duration 0816.srt% Y7 u5 q2 u6 G% o6 A8 ^
│ 8 - 1 - 1 - Introduction to Image Inpainting - Duration 0816.txt8 r+ j) D" T) w. A( n: C9 e0 t/ L0 C
│ 8 - 2 - 2 - Inpainting in Nature - Duration 0501.mp4) S+ W- X) v% p
│ 8 - 2 - 2 - Inpainting in Nature - Duration 0501.srt
2 p; m% A" ^# H9 t4 k/ E+ u │ 8 - 2 - 2 - Inpainting in Nature - Duration 0501.txt! O% a% Q* X* k3 O1 M
│ 8 - 3 - 3 - PDEs and Inpainting - Duration 2159 - Optional break at 1331.mp4
- x- O# h0 l$ ]" n2 y │ 8 - 3 - 3 - PDEs and Inpainting - Duration 2159 - Optional break at 1331.srt
' |$ n4 M; R" [$ c- k' f2 u" D │ 8 - 3 - 3 - PDEs and Inpainting - Duration 2159 - Optional break at 1331.txt8 S4 |' U+ S1 a0 z: i
│ 8 - 4 - 4 - Inpainting via Calculus of Variations - Duration 1532 - Optional break at 1006.mp4- y* P2 {. k/ U, g6 b
│ 8 - 4 - 4 - Inpainting via Calculus of Variations - Duration 1532 - Optional break at 1006.srt5 X: b2 ]" d; D# V) f4 P
│ 8 - 4 - 4 - Inpainting via Calculus of Variations - Duration 1532 - Optional break at 1006.txt
& a) w- M( W4 t4 Y, ^0 i; d* F │ 8 - 5 - 5 - Smart Cut and Paste - Duration 0751.mp4/ c% `9 _+ L: ]2 d( B' _
│ 8 - 5 - 5 - Smart Cut and Paste - Duration 0751.srt _ F+ C! L, H7 x) o
│ 8 - 5 - 5 - Smart Cut and Paste - Duration 0751.txt& Q6 [; y9 N0 S, r- W& Q
│ 8 - 6 - 6 - Demo - Photoshop Inpainting Healing Brush - Duration 0231.mp48 _7 p4 o( ]) H* t4 k
│ 8 - 6 - 6 - Demo - Photoshop Inpainting Healing Brush - Duration 0231.srt
" w; K( |8 j6 |; I9 |* w │ 8 - 6 - 6 - Demo - Photoshop Inpainting Healing Brush - Duration 0231.txt' Q% T' T( T( y8 D! ~' N; [' g
│ 8 - 7 - 7 - Video Inpainting and Conclusions - Duration 0513.mp46 {/ P8 Q+ j+ b$ l x
│ 8 - 7 - 7 - Video Inpainting and Conclusions - Duration 0513.srt6 W- R! p6 y4 g2 [: C2 Q# T
│ 8 - 7 - 7 - Video Inpainting and Conclusions - Duration 0513.txt2 f& |; w. E: v# _" s+ R- H7 }
│ 9 - 1 - 1 - Introduction to Sparse Modeling - Part 1 - Duration 1039 .mp4
a) [8 M9 @) t( ?% R8 T) f* S( D │ 9 - 1 - 1 - Introduction to Sparse Modeling - Part 1 - Duration 1039.mp4
$ K7 N4 `" Z4 w+ c │ 9 - 1 - 1 - Introduction to Sparse Modeling - Part 1 - Duration 1039.srt9 G( j) }0 c, v9 M: ]) L* x
│ 9 - 1 - 1 - Introduction to Sparse Modeling - Part 1 - Duration 1039.txt |
所有IT类厂商认证考试题库下载
2018新版 肖哥 华为HCNA HCNP安全入门课程视频教程
华为HCNP最新战报950分通过。迎战总结。H12-223
大幅提升工作效率~SecureCRT 8.0安装 & 加载配色方案
强大模拟器EVE-NG-PRO 永久免费使用版 无需license 附带使用视频教程
EVE-NG-PRO永久试用版横空出世，Toolkit一键激活！
视频教程 看的见的算法 7个经典应用诠释算法精髓
EVE-NG-PRO专业版国内大神破解版-永久更新
乾颐堂 最新 2018 CCNA安全课程视频教程分享 5天完整版 教主真人秀
INE出品Wireshark教程（初级） 国外英文培训视频 Wireshark抓包技术视频
HCNP RS上海顺利通过！
新版视频 raspberry树莓派3b入门 小汽车 机械臂机器人 蓝牙 wifi
新版视频 raspberry树莓派3b入门传感器开发板套件学习视频教程
[复制链接]
