Interposing an ontogenetic model between Genetic Algorithms and Neural Networks

Part of Advances in Neural Information Processing Systems 5 (NIPS 1992)

Bibtex Metadata Paper

Authors

Richard Belew

Abstract

The relationships between learning, development and evolution in Nature is taken seriously, to suggest a model of the developmental process whereby the genotypes manipulated by the Genetic Algo(cid:173) rithm (GA) might be expressed to form phenotypic neural networks (NNet) that then go on to learn. ONTOL is a grammar for gener(cid:173) ating polynomial NN ets for time-series prediction. Genomes corre(cid:173) spond to an ordered sequence of ONTOL productions and define a grammar that is expressed to generate a NNet. The NNet's weights are then modified by learning, and the individual's prediction error is used to determine GA fitness. A new gene doubling operator appears critical to the formation of new genetic alternatives in the preliminary but encouraging results presented.