Location: McConnell Bldg 13
Times: Tuesdays and Thursdays, 2:30-4:00pm
Instructor: Professor G. Dudek,School of Computer Science.
Office hours: Tues. & Thurs. 1:00-1:30 and 4-4:30; meetings at other times by appointment.
Office: McConnell 419Telephone: 398-4325.
Stuart Russell and Peter Norvig, "Artificial Intelligence: A Modern Approach", Prentice Hall, 1994. 840 pages, estimated price $57.95.
Artificial Intelligence: Theory and Practice by: Thomas Dean, James Allen, Yiannis Aloimonos, Addison-Wesley Longman publishers, 1995. 563 pages.
Bonnie Lynn Webber and Nils J. Nilsson, "Readings in Artificial Intelligence", Morgan Kaufmann, San Mateo, CA, 1981.
Some handouts and class notes may be available on line.
The class web page is available at
much important information will be available there
Teaching Assistants : (tentative)
Yiannis Rekleitis (firstname.lastname@example.org) (SEE NOTE ON EMAIL, ABOVE)
Eric Bourque (email@example.com) (SEE NOTE ON EMAIL, ABOVE)
TA's office hours: To be announced
This class focuses on selected topics in Artificial Intelligence. We will study modern techniques for computers to make good (in some cases optimal) decisions that are applicable throughout an enormous range of industrial, civil, medical, financial, robotic and information systems. We will not attempt to cover the entire range of AI sub-areas in detail, but will survey several key themes.
Evaluation will be based on:
Four assignments together worth 28% of the final mark
A final project worth 26%
A midterm worth 7%
A final exam worth 39%
Minor changes to the evaluation scheme (if any) will be announced in class by Sept. 7 (pending in-class discussion or an estimate of total enrollment).
The assignments will include both written work and implementations. The implementation work will involve programming on UNIX. The ability to program in C under the UNIX operating system is assumed but the use of the C language may not be mandatory.
The final project will involve both computer implementation work and a written paper. Both parts (paper and implementation) are required for a passing grade. A functioning program and a typed paper in with good style are minimum prerequisites for an acceptable project.
Syllabus and Tentative Schedule
There is a chance that some sections will be exchanged in terms of their order of presentation.
Chapter references below are with respect to the supplementary text (DAA: Dean, Allen, Aloimonos) not the primary textbook (RN: Russell and Norvig). Note that some presentations such as that on learning and neural networks deal with material not present in either book.
Overview of AI
(week 1; RN/DAA chapter 1)
Knowledge representation and inference
(weeks 2 &4; chapter 3 &6)
Search (weeks 3 & 5; chapter 4)
Learning and Reasoning
Symbolic learning (week 6; chapter 5, first half)
Learning in neural networks (week 7; chapter 5, second half)
Either (week 8)
Genetic Algorithms (supplementary readings), or
Probabilistic and fuzzy reasoning (chapter 8)
Perception and Action
Vision (week 9 & 10; chapter 9 and supplementary readings)
Action: planning and robotics (week 11; chapter 7)
Natural language (if time permits, week 12; chapter 10)
Review, project discussions
Discussions (week 13)