2110742 Evolutionary Computation 2008

Prabhas Chongstitvatana

Office: Engineering Building 4, floor 18, room 13
phone: 02-2186982
email: prabhas at chula dot ac dot th
class webpage: http://www.cp.eng.chula.ac.th/faculty/pjw/

Class meeting: Tue 10:300-12:00, Eng Bld 3, room 425; Thur 10:30-12:00, Eng. Bld.4, 19-16.

This class discusses evolutionary computation in all aspects. Many established topics in this field will be studied: Genetic algorithms, Genetic programming, Evolution strategies. Advanced topics such as Estimation of distribution algorithms and multiple objective optimisation are included. Theory as well as practical aspects are emphasized.

How the class is conducted?

Because the nature of the topics is the study of algorithms, it renders itself suitable for experimentation. Weekly assignment requires students to run the experiment based on the algorithm in the lecture. It is a graduate class, so students are expected to do a lot of self-study. Individual studies are designed to let students study a specific topic in depth. The results are presented in the group discussion as well as submission of written reports.

Announcement

30 Oct 2008 Please visit the course Wiki (where students exchange ideas)
. . .
Previous lectures 2006 2005 2003 2000

Weekly lecture

1 Probabilistic algorithms
2 Genetic algorithms (Whitley tutorial on GA)
3 Theoretical basis
4 Genetic operators
5 Genetic programming
6 Schema theorem for GP
7 Evolution strategies
8 Estimation of distribution algorithms (Pelikan slides)
9 EDA 2
10 Multiple objective optimisation
11 Group discussion 1
12 Group discussion 2
13 Group discussion 3
14 Summary

External references

Wiki page for the course discussion

http://www.cp.eng.chula.ac.th/~wiki/cpwiki/index.php/User:2110742_EC

Applet (animation) for GA

http://www.rennard.org/alife/english/gavgb.html

Genetic Algorithm Viewer 1.0 is a demonstration applet of the functioning of a Genetic Algorithm (GA). It aims at showing the power of GA and of the main mechanisms used while permitting a certain form of visualization of the general functioning.

http://www.ads.tuwien.ac.at/raidl/tspga/TSPGA.html
Visualisation of Genetic Algorithms for the Traveling Salesman Problem in Java

http://www.stellaralchemy.com/ice/
The applet executes what is called a genetic algorithm (GA). To facilitate understanding, every step in the GA is animated. This particular GA evolves solutions to a simple board game. This program also detects and reports if any irreducibly complex (IC) solutions arise during the evolution of its population of solutions to the board game.

http://www.obitko.com/tutorials/genetic-algorithms/example-function-minimum.php
Minimum of Function: The problem is expressed as looking for extreme of a function. Some function is given and GA tries to find minimum of the function. For other problems we just have to define search space and the fitness function which means to define the function, which we want to find extreme for.

Assessment

homework 20
individual study 30
final exam 50

Text

1. Mitchell, M., An introduction to genetic algorithms, MIT press, 1996.
2. Goldberg, D., The design of innovation, Kluwer pub, 2002.
3. Holland, J. H., Adaptation in natural and artificial systems, MIT press, 1992.
4. Koza, J., "Genetic Programming Vol 1, 2, 3", MIT Press, 1992, 1994, 1999.
5. Goldberg, D., Genetic algorithms, Addison-Wesley, 1989.
6. Banzhaf, W., Nordin, P., Keller, R. and Francone, F., Genetic Programming: An Introduction, Morgan Kaufmann, 1998.
6. Winter, G., Periaux, J., Galan, M., Cuesta, P. (eds), Genetic algorithms in engineering and computer science, John Wiley, 1995.

Uptodate handouts on various current researches will be distributed in the class.

last update 13 Jan 2009