LNCS Homepage
CD ContentsAuthor IndexSearch

Evolving Reusable Neural Modules

Joseph Reisinger, Kenneth O. Stanley, and Risto Miikkulainen

Department of Computer Sciences, The University of Texas at Austin, 1 University Station C0500, Austin, TX 78712-1188
joeraii@cs.utexas.edu
kstanley@cs.utexas.edu
risto@cs.utexas.edu
http://www.cs.utexas.edu/~joeraii
http://www.cs.utexas.edu/~kstanley
http://www.cs.utexas.edu/~risto

Abstract. Topology and Weight Evolving Artificial Neural Networks (TWEANNs) have been shown to be powerful in nonlinear optimization tasks such as double pole-balancing. However, if the input, output, or network structures are high dimensional, the search space may be too large to search efficiently. If the symmetries inherent in many large domains were correctly identified and used to break the problem down into simpler sub-problems (to be solved in parallel), evolution could proceed more efficiently, spending less time solving the same sub-problems more than once. In this paper, a coevolutionary modular neuroevolution method, Modular NeuroEvolution of Augmenting Topologies (Modular NEAT), is developed that automatically performs this decomposition during evolution. By reusing neural substructures in a scalable board game domain, modular solution topologies arise, making evolutionary search more efficient.

LNCS 3103, p. 69 ff.

Full article in PDF


lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004