Evolution and Learning in Neural Networks

Ron Keesing, David G. Stork

Abstract: and *Dept. of Electrical Engineering Stanford University Stanford, CA 94305 [e-mail] Learning can increase the rate of evolution of a population of biological organisms (the Baldwin effect). Our simulations show that in a population of artificial neural networks solving a pattern recognition problem, no learning or too much learning leads to slow evolution of the genes whereas an intermediate amount is optimal. Moreover, for a given total number of training presentations, fastest evoution occurs if different individuals within each generation receive different numbers of presentations, rather than equal numbers. Because genetic algorithms (GAs) help avoid local minima in energy functions, our hybrid learning-GA systems can be applied successfully to complex, high(cid:173) dimensional pattern recognition problems.