Course COM407 Computational Intelligence:
MW 2:45-4:00 Robotics Lab
Professor:
Gary Parker
Winthrop Annex (ext. 5208)
parker@conncoll.edu
Text and Software:
Text:Artificial Intelligence by Michael Negnevitsky. Additional readings will be assigned in class.
Software:The software used for learning programs will be Xpilot-AI, available at http://www.xpilot-ai.org/. Emacs for program editing is available on all Sparc workstations. Emacs can be obtained from GNU Software at: ftp://ftp.gnu.org/gnu/emacs/
Web Page:http://cs.conncoll.edu/com407
Office Hours:
Winthrop Annex: Mon, Wed: 10:00-11:00 and 4:00-5:30
Course Description:
Computational methods that display aspects of intelligent behavior observed in humans. Topics may include fuzzy logic, an alternative to traditional formal logic; artificial neural networks, networks of simple arithmetic computing elements that abstractly simulate neurons; and genetic algorithms, based on the laws of survival of the fittest and natural selection. How these methods deal with vague, imprecise, and uncertain knowledge; learn from experience; self-organize; and adapt their behavior in response to changing conditions to solve real world problems. Utilization of projects and the discussion of technical papers to cover methods of computational intelligence and their use.
Prerequisite: Course 304, Course 310, Course 316, or Course 320.
Discussion:
This course is a study of fuzzy logic, artificial neural networks, and evolutionary computation. Fuzzy logic is an alternative to traditional formal logic that allows one to deal with vague, imprecise, and uncertain knowledge. Artificial neural networks are networks of simple arithmetic computing elements that abstractly simulate neurons. Evolutionary computation uses the observed laws of survival of the fittest and natural selection to find solutions to complex problems. These techniques are complementary to one another and allow for the formation of solutions with features that are often assumed to be signs of intelligence.
The class will be taught in two parts. In the first, we will cocentrate on learning the basics of the three components of computational intelligence. This will be done through readings from the text, lectures, discussions, and homework assignments. The second part will take us more into the advanced issues of fuzzy logic, neural networks, and evolutionary computation. This will be done through the reading / presentation / discussion of technical papers and through the completion of a final project. The project will start with research in your area of interest to determine what you want to do and what work has been done in the past. It will continue with a written proposal. After approval of your proposal, you will start doing the research, making periodic reports on your progress. Finally, you will produce a paper and present it at the end of the semester.
Grading:
Presentations |
15% |
Class Discussion |
15% |
Homework |
25% |
Final Project |
35% |
Computational Intelligence Notebook |
10% |
Presentations:You will make two or three paper presentations; one on an assigned reading and one or two on a paper you find that is pertinent to an assigned subject.
Class Discussion:This portion of the grade includes your class participation and your readiness to defend assigned issues during scheduled debates.
Homework:Homework will be assigned during the first part of the class. In some cases it will be a problem to solve and in other cases it will be a programming assignment. Homework can be done individually or in a team.
Final Project:The project will be on a topic of your choice. The grade includes the proposal, periodic progress reports, a final paper, and a final presentation / demonstration. The project can be done individually or in a team.
Computational Intelligence Notebook::This notebook is for you to organize and summarize what you have learned about Computational Intelligence. It is to have a summary paragraph about each topic that we cover and a copy of the assigned readings marked with your notes and/or comments. The notebooks are to be done individually.
Note:
If you have a physical or mental disability, either hidden or visible, which may require classroom, test-taking, or other reasonable modifications, please see me as soon as possible. If you have not already done so, please be sure to register with Susan L. Duques, Ph.D., in the Office of Student Disability Services, at Extension 5428.