Graduate School of Science and Engineering

Back to List

HUI500X3(人間情報学 / Human informatics 500)
Multimodal Interface

Shoji KURAKAKE

Class code etc
Faculty/Graduate school Graduate School of Science and Engineering
Attached documents
Year 2022
Class code YB036
Previous Class code
Previous Class title
Term 春学期授業/Spring
Day/Period 金4/Fri.4
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)

Students will learn methods for the prediction and classification by using integrally data from multiple modal medium including CNN,RNN,LSTM and ensemble learning, and relevant theory including backpropagation and Expectation-Maximization algorithm. Students will also have an opportunity to investigate the difference on the practical procedures between for the case processing image and audio data and for the case processing data in a financial market. Students are required to make a presentation about the investigation result to other students, which can deepen the understanding of the lessons and improve presentation skills.
[Learning activities outside of classroom]
The review and the preparation of each lesson will take 4 hours. How to use MATLAB should be learnt by students themselves by mainly using web and with the help form the staff at the software center for the setting related things.
[Grading Criteria /Policy]
Grade is determined 20% by the submission of the assignment for each lesson and 80% by the evaluation of the presentation and how effective on the following question-and-answer session.

Default language used in class

日本語 / Japanese