Faculty of Science and Engineering

Back to List

COT300XE(計算基盤 / Computing technologies 300)
Multi-modal Information Processing

Shoji KURAKAKE

Class code etc
Faculty/Graduate school Faculty of Science and Engineering
Attached documents
Year 2022
Class code H6107
Previous Class code
Previous Class title
Term 秋学期授業/Fall
Day/Period 火4/Tue.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)
Notes
Open Program
Open Program (Notes)
Global Open Program
Interdepartmental class taking system for Academic Achievers
Interdepartmental class taking system for Academic Achievers (Notes)
Class taught by instructors with practical experience
SDGs CP
Urban Design CP
Diversity CP
Learning for the Future CP
Carbon Neutral CP
Chiyoda Campus Consortium
Category 応用情報工学科
学科専門科目

Show all

Hide All

Outline (in English)

Multimodal information processing is about technologies for prediction and classification from different modal data, such as image and audio. In this class, students will learn single modal data processing technologies in the first half of the classes. For image processing, convolutional neural network is introduced. For speech recognition, hidden Markova model, RNN and LSTM are explained. In the second half of the classes, student will learn technologies to combine different single modal data processing results. Student will also have opportunities to try MATLAB code provided by the lecturer and deepen the level of understanding for technologies learned through the class.
[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 40% by the submission of the assignment for each lesson and 60% by the evaluation of the final report.

Default language used in class

日本語 / Japanese