Web Syllabus

(2019)

Back Search for Syllabus by Professors

Intelligent Systems

 YAMANE, Ken
  Elective  2 credits
【Master's program･1st semester】
19-3-1002-3192

１．
Outline
We overview classical artificial intelligence and discuss its limitations. Also, this course deals with the following topics: soft-computing, pattern recognition and machine learning.
２．
Objectives
The aim of the course is to learn fundamental concepts and techniques of intelligent systems.
３．
Grading Policy
Students are evaluated with two reports (50%, 50%).
４．
Textbook and Reference
No textbook is used.

The following book written in English is recommended.
-Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Global Edition, Pearson Education Limited, ISBN978-1292153964, 2016.
５．
Requirements (Assignments)
Students should use E-mail and LMS.
６．
Note
Basic skills of programming and the knowledge of computer science are required for students.
７．
Schedule
１. Introduction
２. Classical artificial intelligent I
３. Classical artificial intelligent II
４. Classical artificial intelligent III
５. Limitations of AI
６. Subsumption architecture
７. Soft-computing I
８. Soft-computing II
９. Soft-computing III
10. Soft-computing IV
11. Pattern recognition and machine learning I
12. Pattern recognition and machine learning II
13. Reinforcement learning I
14. Reinforcement learning II
15. Summary
１．
Outline
We overview classical artificial intelligence and discuss its limitations. Also, this course deals with the following topics: soft-computing, pattern recognition and machine learning.
２．
Objectives
The aim of the course is to learn fundamental concepts and techniques of intelligent systems.
３．
Grading Policy
Students are evaluated with two reports (50%, 50%).
４．
Textbook and Reference
No textbook is used.

The following book written in English is recommended.
-Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Global Edition, Pearson Education Limited, ISBN978-1292153964, 2016.
５．
Requirements (Assignments)
Students should use E-mail and LMS.
６．
Note
Basic skills of programming and the knowledge of computer science are required for students.
７．
Schedule
１. Introduction
２. Classical artificial intelligent I
３. Classical artificial intelligent II
４. Classical artificial intelligent III
５. Limitations of AI
６. Subsumption architecture
７. Soft-computing I
８. Soft-computing II
９. Soft-computing III
10. Soft-computing IV
11. Pattern recognition and machine learning I
12. Pattern recognition and machine learning II
13. Reinforcement learning I
14. Reinforcement learning II
15. Summary