Graduate School of Science and Engineering

Back to List

FRI500X3(情報学フロンティア / Frontiers of informatics 500)
Neural Information Processing (Ⅱ)

Hirahara MAKOTO

Class code etc
Faculty/Graduate school Graduate School of Science and Engineering
Attached documents
Year 2022
Class code YB021
Previous Class code
Previous Class title
Term 秋学期授業/Fall
Day/Period 水3/Wed.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 応用情報工学専攻

Show all

Hide All

Outline (in English)

This course deals with machine learning that is one of the fastest growing areas of artificial intelligence. Topics include maximum likelihood method and EM algorithm for density estimation, support vector machine for classification and support vector regression for function approximation. This course places emphasis on mathematical derivation and computer implementation of the learning algorithms. Students are required to have a knowledge of probability, statistics, calculus, algebra, optimization and Excel skills to keep up with this course. At the end of this course, students are expected to derive the learning algorithms and implement them from scratch in Excel. Students will be expected to have completed the required assignments after each class meeting. Before/after each class meeting, students will be expected to spend four hours to understand the course content. Final grade will be calculated according to the following process: homework (70%), quizzes (20%), and in-class contribution (10%).

Default language used in class

日本語 / Japanese