Classroom: Sparks Hall 327, 2:45-4:25 p.m., T TH

Instructor: Dr. Yanqing Zhang

Office: 1445 in One Park Tower at 34 Peachtree

Phone: 404-413-5733 (o)

Fax: 404-413-5717 (o)

E-mail: yzhang@cs.gsu.edu

Website: http://www.cs.gsu.edu/~cscyqz/courses/ai/ai08.html

Office Hours: 1:00 – 2:30 p.m. T Th or by appointment

Text: Artificial Intelligence - A Modern Approach, Second Edition, by S. J. Russell and P. Norvig, Prentice Hall, 2003.

Course Content: Introduction to basic AI techniques and methodologies. Topics include search strategies, problem solving, knowledge and reasoning, logic and deduction, expert systems, neural networks, fuzzy logic, genetic algorithms, learning, data mining, intelligent agents, etc. Hands-on programming projects.

Prerequisite: CSc 3410 Data Structures and CSc 4330 (or 6330) Programming Language Concepts.

Course Requirements: All students should not only learn basic theoretical principles but also accumulate practical hands-on experience. Undergraduate students and graduate students will do assignments, take tests and finish programming projects. At the end of this semester, all graduate students and undergraduate students will give presentations to share knowledge and skills. An undergraduate student needs to write a technical report. A graduate student needs to write a conference paper. Each student does his/her independent research project.

Class Policy:

Ø Attendance: Students are required to attend all classes.

Ø Academic honesty: Plagiarism will result in a score of zero on the test or paper. The instructor has the right to make a decision of if two or more works are cheating.

Ø Assignments and Projects: They must be handed in on time and will not be accepted when past due.

Ø Withdrawals: March 3 Monday is the last day to withdraw and possibly receive a W.

Ø Make-ups: need the instructor's special permission.

Grading Policy:

Mid-term Exam 25%		A [90, 100]
Final Exam 25%		B [80, 90)
Assignments 15%		C [70, 80)
Projects 30%		D [60, 70)
Attendance 5%		F [0, 60)

Tentative Course Outline and Schedule:

Chapter 1 Introduction	Jan 8
Chapter 2 Intelligent Agents	Jan 10, 15
Chapter 3 Solving Problems by Searching	Jan 17, 22, 24
Chapter 4 Informed Search and Exploration	Jan 29, 31, Feb. 5, 7
Chapter 6 Adversarial Search	Feb 12, 14
Chapter 7 Logical Agents	Feb 18, 21
* Mid-term Exam	Feb 26
Chapter 13 Uncertainty	Feb 28, (Spring Break: 3/3-3/9) Mar. 11, 13
Chapter 14 Probabilistic Reasoning	Mar. 18, 20
Chapter 20 Statistical Learning Methods	Mar. 25, 27, April 1, 3
Chapter 21 Reinforcement Learning	April 8, 10
Chapter 27 AI: Present and Future	April 15
# Project Presentations	April 17, 22
* Final Exam (Project Paper Hardcopy and Disk including the paper and programs Due)	April 24 (last class)

Statement: This course syllabus provides a general plan for the course; deviations may be necessary.