Optimal Mate Choice in a Neural Network

Abstract

The tactics of mate choice was studied by means of a simple neural network model. A female was assessing 6 or 43 males and optimal choice was assumed to be the largest male of the set of males visited. This was run over a set of variances in male traits from very low as in fluctuating asymmetry to very high as in ornaments. This was done in two ways: by estimating the mean number of visits to each male before the optimal choice was done, or the probability of choosing the largest male given the constraints of five visits. When an error was introduced in perception the number of visits was very high if variance was low, but levelled off and reached an asymptote at fairly low levels of variance, i.e. variance among males is important only up to a certain level. When the number of visits was constrained the probability of choosing the right male increased with increasing variance. When asymmetry was evaluated the chance of finding the “best” male in five visits was very low (<10%) for the 6-male case, and it never happened in the 43-male case.