Instructor:
Dr. John R. Sullins
Office hours: MW
Office: 333 Meshel Hall
Phone: 742-1806
Email: john@cis.ysu.edu
Web site: http://cis.ysu.edu/~john/
Check the web site regularly, as assignments and announcements will be posted here.
Objectives:
This course is meant to introduce you to important concepts in artificial intelligence, particularly expert systems, robotics, and knowledge acquisition (including neural networks and genetic algorithms), and their use and development in business and other applications. This will include hands-on experience with an expert system shell, a robotic navigation simulator, and a neural network package.
Prerequisites:
CSIS 2617: Data Structures and Objects. In terms of content, you need some programming background. However, the programming for this course will probably not be like any you have done before.
Textbook:
Artificial Intelligence: A Guide to Intelligent Systems, Michael Negnevitsky, Addison Wesley.
Grading:
|
Programming assignments |
25% |
(3 – 4 assignments) |
|
Exam 1 |
15% |
Wednesday, Feb. 25 |
|
Exam 2 |
15% |
Wednesday, March 31 |
|
Final Exam |
20% |
Monday, May 3, |
|
Expert System Project |
25% |
Due last week of classes |
Last day to withdraw with a "W": Saturday, March 20
Programming Assignments:
The programming assignments will generally involve short exercises using an expert system shell (possibly CLIPS or VP-Expert), a Java-based Neural Network package, and a robot navigation simulator. I will provide links to/copies of the software as needed.
As with any other course, work on these assignments must be your own. See the policy sheet for more details.
Project:
The final project will involve implementation of some expert system for a problem of your own choosing using an expert systems shell, as an introduction to the process of knowledge acquisition and expert system development. A project proposal will be required early in the semester, and a written report and class demonstration of the final system will be required the last week of the semester.
Tentative Course Outline:
|
WEEK |
TOPICS |
|
1/12 |
Knowledge representation in intelligent systems |
|
1/19 |
Rule-based expert systems |
|
1/26 |
Expert systems shells: VP-Expert |
|
2/2 |
Expert systems shells: CLIPS |
|
2/9 |
Uncertainty, probability, and fuzzy logic |
|
2/16 |
Representing uncertainty in expert systems shells |
|
2/23 |
Robot sensing and navigation |
|
3/1 |
Application of AI techniques to robotics |
|
3/8 |
SPRING BREAK |
|
3/15 |
Knowledge acquisition and validation in expert systems |
|
3/22 |
Neural network learning and discovery |
|
3/29 |
Applications of neural networks |
|
4/5 |
Genetic learning algorithms |
|
4/12 |
Frame-based expert systems |
|
4/19 |
Hybrid expert systems, Data mining |
|
4/26 |
Project presentations |