CSCI/ENGR 8940 Computational Intelligence

CSCI/ENGR 8940 Computational Intelligence (GA part)

Spring 2003: Mondays and Thursdays 3:30 - 4:20pm, Driftmier-601

Instructor: Prof. Khaled Rasheed (Prof. Ron McClendon will teach the Neural Networks portion of the course)
Telephone: (706)542-3444
Office Hours: Tuesday: 2pm-5pm
Office Location: Room 219B, Boyd GSRC
Email: khaled@cs.uga.edu


Objectives:

To provide a broad introduction to the field of Genetic Algorithms (GA) and other fields of Evolutionary Computation and global optimization. To teach students how to apply these methods to solve problems in complex domains such as Engineering design and Optimization. The course is appropriate both for students preparing for research in Artificial Intelligence, and Engineering students who want to apply AI techniques to solve problems in their fields of study.

Recommended Background:

CSCI/PHIL 4550/6550 Artificial Intelligence (or permission of the instructor). Familiarity with basic computer algorithms and data structures and at least one high level programming language.

Topics to be Covered:

Genetic Algorithm core topics including representation, operators and architectures. Genetic Algorithm applications in Engineering optimization including design. Other fields of evolutionary computation. Other global optimization techniques such as simulated annealing.

Expected Work:

Reading; assignments (including programming); midterm; and term project and paper. (Unless otherwise announced by the instructor: all assignments and all exams must be done entirely on your own.)

Academic Honesty and Integrity:

All students are responsible for maintaining the highest standards of honesty and integrity in every phase of their academic careers. The penalties for academic dishonesty are severe and ignorance is not an acceptable defense.

Grading Policy:

  • Assignments: 25% (Programs, questions, attendance, paper presentations)
  • Midterm Examination: 25%
  • Final Examination: 25%
  • Term Project: 25% (includes term paper and presentation)
    Students may work on their term projects in groups of up to three students each. The above distribution is only tentative and may change later. The instructor will announce any changes.

    Assignment Submission Policy

    Assignments must be turned in by the assigned deadline. Late assignments will not be accepted. Rare exceptions may be made by the instructor only under extenuating circumstances and in accordance with the university policies.

    Course Home-page

    A variety of materials will be made available on the CI Class Home-page at http://cobweb.cs.uga.edu/~khaled/CIcourse/, including handouts, lecture notes and assignments. Announcements may be posted between class meetings. You are responsible for being aware of whatever information is posted there.

    Lecture Notes

    Copies of some of Dr. Rasheed's lecture notes will be available at the bottom of the class home page. Not all the lectures will have electronic notes though and the students should be prepared to take notes inside the lecture at any time.

    Textbook in Bookstore

  • "Genetic Algorithms + Data Structures = Evolution Programs", Zbigniew Michalewicz. Springer-Verlag, New York,1996. (Required)

    Additional Books

  • "Genetic Algorithms in Search, Optimization, and Machine Learning", David Goldberg. Addison-Wesley, 1989.
  • "An Introduction to Genetic Algorithms", Melanie Mitchell. MIT Press, 1996.
  • "Evolutionary Algorithms in Engineering Applications", D. Dasgupta and Z. Michalewicz(editors). Springer-Verlag, New York,1997.
  • "Genetic Algorithms and Engineering Optimization", Mitsuo Gen and Runwei Cheng. John Wiley & Sons Inc., 2000.

    Announcements:

  • [5-1-2003] All scores are posted HERE. Please make sure that all your scores are properly recorded.
  • [4-14-2003] We will cover Multi-objective GAs from the handout posted below (in lecture notes).
  • [3-6-2003] The projected grades and all scores are posted HERE. Please make sure that all your scores are properly recorded.

    Papers

  • "Constrained Multi-objective Optimization Using Steady State Genetic Algorithms" D. Chafekar et al., 2003.[S. Hardas,M. Kaijima][4-21]{Download}
  • "Hexapod walking robot for agricultural field" M. dohi et al., 2002. [S. Utley, J. Kessler][]{Download}
  • "Evolutionary Algorithms for Neural Network Design and Training" J. Branke , 1995. [B. Qian, C. Zhang][4-23] {Download}
  • "Interactive design of web sites with a genetic algorithm" A. Oliver et al., [Achim, Joschka] [4-24] {Download}
  • "Application of Genetic Algorithms to Texture Analysis" P. Salik et al., 1999. [K. Tariman, R. Aggarwal] {Download}
  • "Hierarchical Rank Density Genetic Algorithm for Radial-basis Function Neural Network Design" Gary G. Yen Haiming Lu, 2002. [Hajime,Ning][] {Download}

    Assignments:

  • Assignment 1
  • Assignment 2
  • Assignment 3
  • Assignment 4

    Lecture Notes:

  • Introduction,Compressed
  • Multi-objective GAs

    Last modified: May 1, 2003.

    Khaled Rasheed (khaled@cs.uga.edu)