Download:
|
by William M. Spears
Proceedings of the Fourth Annual Conference on Evolutionary Programming
http://www.aic.nrl.navy.mil/~spears/papers/ep95.ps.gz
Add To MetaCart
Abstract:
One of the issues in evolutionary algorithms (EAs) is the relative importance of two search operators: mutation and crossover. Genetic algorithms (GAs) and genetic programming (GP) stress the role of crossover, while evolutionary programming (EP) and evolution strategies (ESs) stress the role of mutation. The existence of many different forms of crossover further complicates the issue. Despite theoretical analysis, it appears difficult to decide a priori which form of crossover to use, or even if crossover should be used at all. One possible solution to this difficulty is to have the EA be self-adaptive, i.e., to have the EA dynamically modify which forms of crossover to use and how often to use them, as it solves a problem. This paper describes an adaptive mechanism for controlling the use of crossover in an EA and explores the behavior of this mechanism in a number of different situations. An improvement to the adaptive mechanism is then presented. Surprisingly this improvement can also be used to enhance performance in a non-adaptive EA.
Citations
|
5172
|
Genetic Algorithms
– Goldberg
- 1989
|
|
685
|
An analysis of the behavior of a class of genetic adaptive systems
– Jong
- 1975
|
|
488
|
Evolutionsstrategie: optimierung technischer systeme nach prinzipien der biologischen evolution
– Rechenberg
- 1973
|
|
473
|
Artificial intelligence through simulated evolution
– Fogel, Owens, et al.
- 1966
|
|
446
|
Uniform crossover in genetic algorithms
– Syswerda
- 1989
|
|
403
|
Numerical Optimization of Computer Models
– Schwefel
- 1981
|
|
287
|
Optimization of control parameters for genetic algorithms
– Grefenstette
- 1986
|
|
259
|
Handbook of Evolutionary Computation
– Fogel
- 1997
|
|
181
|
A survey of evolution strategies
– Back, Hoffmeister, et al.
- 1991
|
|
159
|
Modeling genetic algorithms with Markov chains
– Nix, Vose
- 1992
|
|
146
|
A study of control parameters affecting online performance of genetic algorithms for function optimization
– Schaffer, Caruana, et al.
- 1989
|
|
91
|
An adaptive crossover distribution mechanism for genetic algorithms
– Schaffer, Morishima
- 1987
|
|
61
|
Crossover or mutation
– Spears
- 1993
|
|
51
|
Comparing genetic operators with Gaussian mutations in simulated evolutionary processes using linear systems
– Fogel, Atmar
- 1990
|
|
48
|
A Formal Analysis of the Role of Multi-Point Crossover in Genetic Algorithms
– Jong, Spears
- 1992
|
|
46
|
Dynamic control of genetic algorithms using fuzzy logic techniques
– Lee, Takagi
- 1993
|
|
46
|
An analysis of the interacting roles of population size and crossover in genetic algorithms
– DeJong, Spears
- 1990
|
|
45
|
Recombination distributions for genetic algorithms
– Booker
- 1992
|
|
36
|
On Crossover as an Evolutionarily Viable Strategy
– Schaffer, Eshelman
- 1991
|
|
35
|
Using markov chains to analyze gafos
– Jong, Spears, et al.
- 1995
|
|
31
|
Schema disruption
– Vose, Liepins
- 1991
|
|
22
|
Adapting crossover in a genetic algorithm
– Spears
- 1992
|
|
18
|
De Jong
– Spears, A
- 1991
|
|
15
|
Learning strategy parameters in evolutionary programming: An empirical study
– Saravanan, Fogel
- 1994
|
|
7
|
Adaptation in natural and artifi cial systems
– Holland
- 1975
|
|
4
|
An overview of evolutionary algorithms for parameter optimization. Submitted to the Journal of Evolutionary Computation
– ck, Schwefel
- 1993
|
|
3
|
A Study of Crossover Operators
– Spears, Anand
- 1991
|
|
1
|
An Analysis of of the Interact - ing Roles of Population Size and Crossover in Genetic Algorithms
– Jong, Spears
- 1990
|
