| | |
Summary: GA Issues
Peter G. Anderson,
Computer Science Department
Rochester Institute of Technology,
Rochester, New York
anderson@cs.rit.edu http://www.cs.rit.edu/
February 2004
pg. 1
Abstract
A discussion of the parameters for GAs and how to go about
systematically, intelligently determining their values.
pg. 2
Parent Selection
Selection is a primary tool of a GA. (The other main tool is crossover.)
Here is a common technique: let F =
popsize
j=1 fitnessj
Select individual k to be a parent with probability fitnessk/F
There are some problems here:
· fitnesses shouldn't be negative
|
