Day / Time: Tuesday 17:45-8:25pm
Credit Hours: 3
Prerequisite : MCS 2534 (Data Structures) and (C++, Java)
Lecture Room: S220 (may be changed)
Lab.: CW21 (for some lectures, and if you choose robotics project)
Instructor: Chan-Jin Chung, Ph.D.

• Office Room: Science 112
• Phone: (248) 204-3504
• Fax: (248) 204-3518 (this fax number is for the whole building and senders should be sure to place instructor's name on the fax)
• Dept. Secretary: (248) 204-3560
• Math/CS Drop Box: in front of S120 door.
• Email: CHUNG@ltu.edu
• LTU webpage at http://www3.ltu.edu/~chung (syllabus, announcements, lecture notes, etc.)
• Black Board for the class
• Office Hours: check out http://www3.ltu.edu/~chung and click on office hours

• Title: Artificial Intelligence: A New Synthesis
• ISBN 1-55860-467-7, March 1998
• Author: Nils J. Nilsson

• Artificial Intelligence, 3/e, 1992, 750 p., Patrick Henry Winston, Massachusetts Institute of Technology, ISBN: 0-201-53377-4
• Artificial Intelligence: A Guide to Intelligent Systems , Michael Negnevitsky, S352 pages, 1st edition (September 15, 2001), Addison Wesley Publishing; ISBN: 0201711591

Internet Resources

• the American Association for Artificial Intelligence (AAAI)
• AI topics
• IEEE intelligent systems
• Many more...

Course Objectives

• Introduction to Artificial Intelligence and adaptability theories and techniques, methodologies, and algorithms (simulation of intelligence in computers) (60%)
• Applying theories and techniques to the development of practical Intelligent Systems as class projects (39%)
• To plan next classes such as MSCS capstone project I and II for MSCS students (1%)

Introduction: Fundamental issues in Intelligent Systems (Chap 1) [1 week]

Search and Optimization methods (Chap 7, 8, 9, 11, 12) [5 weeks]

• Generate and Test and Problem Reduction

• Nets and Space-State Search

• Basic Search (Uninformed Search), Heuristic Search and Optimal Search

• Trees and Adversarial Search

• Constrained Search, Constraint satisfaction

• Nonlinear Function Optimization

• Planning

Learning, Adaptation, and Reactive Machines (Chap. 2, 3, 4) [5 weeks]

• Decision tree learning

• Introduction to Version Space

• Learning by Training Perceptrons

• Learning by Training Artificial Neural Nets

• Learning by Simulating Evolution

Autonomous Robotics and Robot Vision (chap. 6, +) [3 week]

Tentative Schedule 

Class Format and Grading: Total 200 points

• Homework assignments and project - 100 points
• 1 midterm: 40 points 
• 1 final (everything covered in class) - 60 points

Class Policies

• Attendance is essential to doing well in the course. The exams will focus primarily (but not exclusively) on material presented in the lectures.
• If you are unable to attend a meeting, it is your responsibility to obtain the material from other students or instructor.

Exam. Policies

• There will be no makeup exams will be given.
• Closed books, closed notes by default; and closed neighbors.

• Homework programming assignments must be done individually.
• Source codes must follow good programming standrads such as commenting, indentation, and meaningful names.
• Must be submitted at the beginning of the class on the due date.
• Late submission penalty is 30%.
• No submission will be accepted beyond a week after the due date.
• Some homeworks are for class competions based on the results. Winners will be recognized in variuos ways.

Students are supposed to select one project from the following table (A group project may be possible):

Policy on Academic Misconduct

• Plagiarism is a serious academic offense. DO NOT COPY THE WORK OF OTHERS. Failure to observe this will result in zero point for the assignment and will be handled in accordance with University Policy.
• Cheating during exams is also a very serious academic offense and will be handled in accordance with University Policy.