outline (see also topics...)

The material to be covered may change a bit depending on class interest but the MAJOR TOPICS are as follows:

  1. Basic principles of evolution, overview of Evolutionary Computation
  2. Introduction to Genetic Algorithms (GA)
  3. GA theory, schema theorem, selection, fitness normalization, GA design principles,
    extensions of GA
  4. GA applications: Traveling Salesman, Job Shop Scheduling, etc.
  5. Coevolutionary (antagonistic and mutualist) GAs
  6. Genetic Programming (GP), schema theorem for GP
  7. Automatically Defined Functions, Subroutine Generalization, Program Architecture Evolution
  8. GP applications: symbolic regression, real-time GP for robot control, examples of
    'human-competitive' GP applications
  9. Anticipatory Classifier Systems, reinforcement learning, Evolution Strategies
  10. Overview of ALife, DNA and molecular computing
  11. Swarm intelligence, ant optimization algorithms
  12. Examples of and design principles for self-organizing systems


    PRESCRIBED TEXT(S): None.

     I'll occasionally recommend readings during class.

Course notes will be posted on this site after each lecture.

Academic Accommodation

You may need special arrangements to meet your academic obligations during the term because of disability, pregnancy or religious obligations. Please review the course outline promptly and write to me with any requests for academic accommodation during the first two weeks of class, or as soon as possible after the need for accommodation is known to exist.

It takes time to review and consider each request individually, and to arrange for accommodations where appropriate. Please make sure you respect these timelines particularly for in-class tests, mid-terms and final exams, as well as any change in due dates for papers.

You can visit the Equity Services website to view the policies and to obtain more detailed information on academic accommodation at http://carleton.ca/equity/accommodation

© Franz Oppacher 2014