2019 Machine Learning (ICT)

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
Undergraduate major in Information and Communications Engineering
Instructor(s)
Kumazawa Itsuo  Nakahara Hiroki 
Course component(s)
Lecture
Mode of instruction
 
Day/Period(Room No.)
Mon7-8(W331)  Thr7-8(W331)  
Group
-
Course number
ICT.S311
Credits
2
Academic year
2019
Offered quarter
3Q
Syllabus updated
2019/9/17
Lecture notes updated
2019/12/10
Language used
Japanese
Access Index
Supplementary documents 

Lecture

Lecture 1 Backgrounds and the summary of the first half of the course. Biological neural networks and their modellings for engineering. Computation and programing of the models.

2019.9.26(Thu.) 7-8Session

Lecture

Lecture 2 Basic mathematics needed for computation, learning and programing of the multi-layer neural networks part 1 (activation functions, SoftMax, logistic regression, gradient descend, chain rule)

2019.9.30(Mon.) 7-8Session

Lecture

Lecture 3 Basic mathematics needed for computation, learning and programing of the multi-layer neural networks part 2 (backpropagation and its recursive computation)

2019.10.3(Thu.) 7-8Session

Lecture

Lecture 4 Programming techniques for multi-layer neural networks and their learning.

2019.10.7(Mon.) 7-8Session

Lecture

Lecture 5 Computation of Convolutional Neural Network (convolution, pooling, SoftMax and their roles) and techniques to improve its performance (generalization capability and avoiding over fitting)

2019.10.17(Thu.) 7-8Session

Lecture

Lecture 6 Mathematics for learning of Convolutional Neural Network (Gradient Descend and Backpropagation)

2019.10.21(Mon.) 7-8Session

Lecture

Lecture 7 Programing and implementation of learning of Convolutional Neural Network

2019.10.24(Thu.) 7-8Session

Lecture

Lecture 8  

2019.10.28(Mon.) 7-8Session

Lecture

Lecture 9 Introduction of machine learning, and Python programming for machine learning.

2019.10.31(Thu.) 7-8Session

Lecture

Lecture 10 Least squares method, overfitting, sparse learning, and robust learning.

Lecture

Lecture 11 Classification problem programming using the scikit-learn library. Logistic regression, support vector machine (SVM), and decision tree.

Lecture

Lecture 12 Clustering including k-means method. Post/pre-processing for a dataset. L1 regularity, measurement of feature, and missing value.

2019.11.11(Mon.) 7-8Session

Lecture

Lecture 13 Maximum likelihood estimation, EM algorithm, Bayesian inference, confidence value.

Lecture

Lecture 14 Data compression, principal component analysis (PCA), linear Discriminant Analysis (LDA), Kernel PCA.

2019.11.18(Mon.) 7-8Session

Lecture

Lecture 15 Ensemble learning, majority method, random forest, bugging, bootstrap method, under boost.

2019.11.21(Thu.) 7-8Session

Lecture

Lecture 16 Exercises and examination of the course, and a programming exercise.

2019.11.25(Mon.) 7-8Session

Get Adobe Reader

It is necessary for those who refer to the PDF file to use "Adobe Reader" as the plug-in software of Adobe System Company.
If you don't have the software, please download from this item (free).

Creative Commons License