Artificial Intelligence
TeachersYAMANE, KenStaffInfo
Grade, SemesterYear 3 2nd semest [Department of Information and Electronic Engineering, Faculty of Science and Engineering]
CategorySpecial Subjects
Elective, CreditsElective 2credit
 Syllabus Number3B324

Course Description

We overview artificial intelligence and discuss its limitations and future. Also, this class deals with the following topics; history of AI, classical AI, reinforcement learning, deep leaning, expert system, neural network, Bayes' theorem, symbol grounding problem, frame problem, etc.

Course Objectives

The aim of the course is to learn fundamental methods and techniques of artificial intelligence.

Grading Policy

Students are evaluated with mini-reports in each lecture (30%), a mid-term exam (30%) and a term exam (40%).

Textbook and Reference

TextbookA Japanese book (ISBN978-4-7973-7026-3) is used.

Following textbooks written in English are recommended.
-Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Global Edition, Pearson Education Limited, ISBN978-1292153964, 2016.
-Rolf Pfeifer, Christian Scheier, Understanding Intelligence, ISBN978-0262661256, 2001.


In this class, students need to actively think, discuss and solve toy problems rather than passively listen to lectures.



1Introduction: what is artificial intelligence (AI)?
2History of AI: the birth of AI (Dartmouth Conference), good old-fashioned AI, AI winter, AI boom, technological singularity, etc.
3Machine learning, reinforcement learning, genetic algorithm, deep learning, etc.
4Expert system, board game AI, narrow AI, etc.
5Neural networks
6Data mining, search algorithm, Bayes' theorem, etc.
7Game theory, game AI, minimax, etc.
8Summary, mid-term exam
9Subsumption architecture, fuzzy logic, etc.
10Natural language processing, machine translation, conversational agent, etc.
11Decision making algorithm, artificial life, etc.
12Symbol grounding problem
13Frame problem
14Future of AI
15Summary, final exam