Title

Enhancing Es-Hyperneat To Evolve More Complex Regular Neural Networks

Keywords

HyperNEAT; NEAT; Neuroevolution

Abstract

The recently-introduced evolvable-substrate HyperNEAT algorithm (ES-HyperNEAT) demonstrated that the placement and density of hidden nodes in an artificial neural network can be determined based on implicit information in an infinite-resolution pattern of weights, thereby avoiding the need to evolve explicit placement. However, ES-HyperNEAT is computationally expensive because it must search the entire hy-percube, and was shown only to match the performance of the original HyperNEAT in a simple benchmark problem. Iterated ES-HyperNEAT, introduced in this paper, helps to reduce computational costs by focusing the search on a sequence of two-dimensional cross-sections of the hypercube and therefore makes possible searching the hypercube at a finer resolution. A series of experiments and an analysis of the evolved networks show for the first time that iterated ES-HyperNEAT not only matches but outperforms original HyperNEAT in more complex domains because ES-HyperNEAT can evolve networks with limited connectivity, elaborate on existing network structure, and compensate for movement of information within the hypercube. Copyright 2011 ACM.

Publication Date

8-24-2011

Publication Title

Genetic and Evolutionary Computation Conference, GECCO'11

Number of Pages

1539-1546

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1145/2001576.2001783

Socpus ID

84860402468 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84860402468

This document is currently not available here.

Share

COinS