IIST (Institute of Integrated Science and Technology)

Back to List

HUI500D1(人間情報学 / Human informatics 500)
IIST Special Lecture 4
IIST特別講義4: Machine Learning

Keping YU

Class code etc
Faculty/Graduate school IIST (Institute of Integrated Science and Technology)
Attached documents
Year 2022
Class code YD968
Previous Class code
Previous Class title
Term
Day/Period
Class Type
Campus 小金井 / Koganei
Classroom name 各学部・研究科等の時間割等で確認
Grade
Credit(s) 2
Notes
Class taught by instructors with practical experience

Show all

Hide All

Outline and objectives

This course provides a broad introduction to machine learning. Topics include regression, classification, meta learning, reinforcement learning, network compression, and so on.

Goal

The students will get to understand the key techniques in machine learning and gain practice implementing them and getting them to work for themselves.

Default language used in class

英語 / English

Method(s)(学期の途中で変更になる場合には、別途提示します。 /If the Method(s) is changed, we will announce the details of any changes. )

It will be given in the Learning Management System. Please confirm the announcement from the Learning Management System.
The students will be asked to submit projects on the basic machine learning problems and consider their own solutions. The students will be encouraged not only to learn the knowledge but also to think about how it can be used to solve real problems.

Active learning in class (Group discussion, Debate.etc.)

あり / Yes

Fieldwork in class

あり / Yes

Schedule

授業形態/methods of teaching:対面/face to face

※各回の授業形態は予定です。教員の指示に従ってください。

1[未定/undecided]:Introduction

What is machine learning? What is supervised learning? What is unsupervised learning?

2[未定/undecided]:Linear regression with one variable

Model representation, cost function, gradient descent for linear regression.

3[未定/undecided]:Linear regression with multiple variables

Multiple features, gradient descent for multiple variables.

4[未定/undecided]:Logistic regression

Classification, hypothesis representation, cost function,

5[未定/undecided]:Regularization

The problem of overfitting, regularized linear regression.

6[未定/undecided]:Neural networks

Non-linear hypotheses, neurons and the brain, model representation.

7[未定/undecided]:Back-propagation algorithm.

Back-propagation algorithm, gradient checking, random initialization.

8[未定/undecided]:Machine learning system design

Examples of implementing machine learning system.

9[未定/undecided]:Meta learning

Introduction and case study of meta learning

10[未定/undecided]:Reinforcement learning

Introduction of reinforcement learning

11[未定/undecided]:Anomaly detection

Introduction and case study of anomaly detection

12[未定/undecided]:Network compression

Introduction and examples of network compression

13[未定/undecided]:More examples and summary

Introduce more examples and summarize the lecture

14[未定/undecided]:Project presentation

Students report their projects.

Work to be done outside of class (preparation, etc.)

【Preparatory study and review time for this class are 4 hours each.】Homework and final presentation.

Textbooks

Handouts and prints will be distributed.

References

Ian Goodfellow, "Deep learning".

Grading criteria

Homeworks 30% + Final report 70%

Changes following student comments

None in particular.