305451 Advanced Artificial Intelligence (2-2)

Academic year: 2549              Semester: 1

 

Instructor Contact Information

Instructor: Suradet Jitprapaikulsarn

Office: EE-408

E-mail: suradet at nu.ac.th

 

Course Overview

Artificial Intelligence is a very broad field covering anything from logic, probability, and continuous mathematics; perception, reasoning, learning, and action; and microelectronic devices to robotic planetary explorers.  In this course we will apply the Artificial Intelligence concepts toward the development of Computer Games.  Students will develop approximately one game each week.

 

Course Objectives

After completing this course, students should have a basic practical understanding of the following:

  1. The methods for deciding what to do when one needs to think ahead several steps.
  2. The ways to represent knowledge and how to reason logically.
  3. How to use the above reasoning methods to decide what to do.
  4. How to reasoning and decision making in the presence of uncertainty.
  5. The methods for generating the knowledge.

 

Instructional Approach

We will use the same textbooks as the last semester.  The additional reference books are also helpful.  Students are required to write programs to demonstrate their understanding of the concept.  Each month student will review literature on artificial intelligence and/or game programming to expand the knowledge beyond what available in the textbooks.

 

Textbook

Reference

  1. Michael Negnevitsky, Artificial Intelligence: A Guide to Intelligent Systems, 2nd Edition, Addison-Wesley, 2005, ISBN 0-321-20466-2
  2. Wendy Stahler, Fundamentals of Math and Physics for Game Programmers, Prentice Hall, 2005, ISBN 0-13-168742-5
  3. John P. Flynt and Omar Salem, Software Engineering for Game Developers, Thomson Learning, 2005, ISBN 1-59200-155-6

 

Course Outline

Week No.

Topics

1

Making Simple Decisions

2

Making Complex Decisions

3

Planning

4

Uncertainty

5

Probabilistic Reasoning

6

Math and Physics for Game Programming: I

7

Math and Physics for Game Programming: II

8

Midterm Examination

9

Knowledge Representation

10

Learning from Observations

11

Knowledge in Learning

12

Statistical Learning Methods

13

Communication

14

Probabilistic Language Processing

15

Perception

16

Conclusion

17

Final Examination

 

Course Evaluation

The course grade will be based on

Item

Weight

Assignments

45%

Literature reviews

10%

Notes & Journal

5%

Exams

40%

 

Academic Policy

 

Notes

The above description is only tentative; it may be changed at the instructor’s discretion.



Last update 29 May 2006, 21:25
Copyright © 2006 Suradet Jitprapaikulsarn