Comparison of multi-layer perceptrons and simple evolving connectionist systems over the Lincoln aphid data set

Abstract

This report presents two further experiments over the aphid data set. The first is an evaluation of the adaptive abilities of backpropagation of errors trained MLP and a comparison of these capabilities with the Simple Evolving Connectionist System (SECoS). The goal of the first experiment is to compare both the performance and the adaptive abilities of the two models. The second experiment is an investigation of the sensitivity of the SECoS to the exclusion of various input variables. The goal of the second experiment is to determine which of the thirteen input variables contributes the most to the modelling of the problem, that is, which variable the network is most sensitive to.