Mixing Different Search Biases in Evolutionary Learning Algorithms

Authors:
Kristina Davoian;Wolfram-M. Lippe
Affiliations:
Department of Mathematics and Computer Science, University of Münster, Münster, Germany 48149;Department of Mathematics and Computer Science, University of Münster, Münster, Germany 48149
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 4
Cited 0

An Analysis of Evolutionary Algorithms Based on Neighborhood and Step Sizes

EP '97 Proceedings of the 6th International Conference on Evolutionary Programming VI
Scaling Up Evolutionary Programming Algorithms

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Soft-Computing: mit Neuronalen Netzen, Fuzzy-Logic und Evolutionären Algorithmen (eXamen.press)

Soft-Computing: mit Neuronalen Netzen, Fuzzy-Logic und Evolutionären Algorithmen (eXamen.press)
Evolutionary programming made faster

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work investigates the benefits of using different distribution functions in the evolutionary learning algorithms with respect to Artificial Neural Networks' (ANNs) generalization ability. We examine two modification of the recently proposed network weight-based evolutionary algorithm (NWEA), by mixing mutation strategies based on three distribution functions at the chromosome and the gene levels. The utilization of combined search strategies in the ANNs training implies that different step sizes determined by mixed distributions will direct the evolution towards good generalized ANNs.