Statistical Learning Theory, Part I


Sumio Watanabe


ai_image2017




Lecture in Department of Mathematical and Computing Science, Tokyo Institute of Technology.


(1) Basic concepts in Statistical Learning Theory
Lecture Note 1 , Classification by a neural network, mp4 file , MATLAB file


(2) Gradient Descent
Lecture Note 2 , Steepest Descent, mp4 file , Accelerater, mp4 file , Stochastic, mp4 file , MATLAB file


(3) Neural Network
Lecture Note 3 , Ridge and Lasso, mp4 file , Training Data , Test Data , Graph Drawing , MATLAB file


(4) Boltzmann Machine
Lecture Note 4 , Associative Memory, mp4 file , Training Data , MATLAB file


(5) Deep Learning
Lecture Note 5 , Sequential Learning, mp4 file , Convolutional Neural Network, mp4 file ,
(Sequential Learning) MATLAB file 1 , MATLAB file 2 , Training Data , Test Data ,
(Convolutional Neural Network) MATLAB file 3 , MATLAB file 4 , Training Data


(6) Entropy and Information
Lecture Note 6 , KL information of Learning Process, mp4 file , MATLAB file


(7) Learning and Generalization
Lecture Note 7 , Normal mixture K=3, mp4 file , Normal mixture K=2, mp4 file , Normal mixture K=5, mp4 file , MATLAB file


(8) Knowledge Discovery and Free Energy
Lecture Note 8 ,
(Realizable Case) Model Selection by AIC and BIC, mp4 file , MATLAB file
(Unrealizable Case) Model Selection by AIC and BIC, mp4 file , MATLAB file