Graduate School of Computer and Information Sciences

Back to List

COT500K1（計算基盤 / Computing technologies 500）
Global CIS Special Lecture 1
グローバルCIS特別講義1

Kaoru UCHIDA

Class code etc
Faculty/Graduate school Graduate School of Computer and Information Sciences
Attached documents
Year 2022
Class code TZ026
Previous Class code
Previous Class title
Term 秋学期授業/Fall
Day/Period 月3/Mon.3
Class Type
Campus 小金井
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
Category

Show all

Hide All

Outline and objectives

Practical machine learning:
This course is designed to give graduate students the fundamental knowledge and practical training of machine learning techniques for intelligent media processing, and how to apply them to real world problems.

Goal

The goal of this course is to have students familiarized with knowledge, understanding, and practices of the process and methodology for machine learning.

Which item of the diploma policy will be obtained by taking this class?

Among diploma policies, "DP1" and "DP2" are related.

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. ）

The course, conducted in English, will mainly consist of lectures but time will be given for students to work on research and programming exercises. Students will enjoy related practical Python programming using code samples provided by the instructor.
Project/assignment outputs will be reviewed in the classroom.

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

あり / Yes

Fieldwork in class

なし / No

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[対面/face to face]：Introduction

Introduction to data science and machine learning

2[対面/face to face]：Data science

Data acquisition and visualization

3[対面/face to face]：Classification 1

Basic techniques and performance measures

4[対面/face to face]：Classification 2

Generalization and overfitting

5[対面/face to face]：Classification 3

Advanced techniques and applications

6[対面/face to face]：Data collection

Web scraping and other techniques

7[対面/face to face]：Regression 1

Linear regression

8[対面/face to face]：Regression 2

Other techniques and applications

9[対面/face to face]：Midterm project

Midterm project workshop

10[対面/face to face]：Clustering 1

Basic techniques

11[対面/face to face]：Clustering 2

Other techniques and applications

12[対面/face to face]：Dimensionality reduction

Basic techniques and applications

13[対面/face to face]：Deep learning

Introduction to neural networks and deep learning

14[対面/face to face]：Final Project

Final project workshop

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

Reading, research and programming assignments.
Standard study time outside of class for preparation and review: 4 hours.

Textbooks

Course materials will be provided in class.

References

Andreas C. Müller,‎ Sarah Guido, "Introduction to Machine Learning with Python: A Guide for Data Scientists," O'Reilly Media, 2016.
Sebastian Raschka, “Python Machine Learning: Unlock Deeper Insights into Machine Learning With This Vital Guide to Cutting-edge Predictive Analytics,” Packt Publishing, 2015.
Willi Richert and Luis Pedro Coelho, "Building Machine Learning Systems With Python," Packt Publishing, 2013.

Grading criteria

Students will be evaluated on the basis of contribution in class (20%), and assignment outputs (80%).

Changes following student comments

(None in particular.
Feedback from students will be encouraged throughout the course.)

Equipment student needs to prepare

Students are expected to bring and use their laptop PCs for in-class programming exercises and presentations.