Recombination and unsupervised learning: effects of crossover in the genetic optimization of neural networks

Abstract

Genetic algorithms have been successfully used for optimizing complex functions over multidimensional domains, such as the space of the connection weights in a neural network. A feed-forward layered network is used to simulate the life cycle of a synthetic animal that moves in an environment and captures food objects. The adaptation of the animal (i.e. of the network's weight matrix) to the environment can be measured by the amount of reached food objects in a given lifetime. We consider this amount as a fitness function to be optimized by a genetic algorithm over the space of the connection weights. The network can learn the weights that solve the survival task only by means of its genetic evolution. The recombination genetic operator (crossover) can be seen as a model of sexual recombination for the population, while mutation models agamic reproduction. The central problem in trying to apply crossover is the difficult mapping between the genetic code string (genotype) and the network's weight matrix (phenotype). For this reason crossover has been considered unsuitable for this kind of problem in the past. In this paper we propose a simple mapping and compare the effects of sexual versus agamic reproduction in such a problem. The results of several parametric simulations are outlined, showing that crossover actually helps to speed up the genetic learning.