Publication Details
Overview
 
 
 

Unpublished contribution to conference

Abstract 

Feature Selective Neuroevolution of Augmenting Topologies (FSNEAT) and Feature De-selective Neuroevolution of Augmenting Topologies (FD-NEAT) are two well-known methods for optimizing the topology and the weights of Artificial Neural Networks (ANNs) while simultaneously performing feature selection. Literature has shown that starting the evolution with ANNs of one hidden layer can affect FD-NEAT's and FS-NEAT's performances. However, no study exists that investigates the e.ects of changing the networks' initial connectivity. In this paper we investigate how the choice of the number of initially connected inputs a.ects the performance of FD-NEAT and FS-NEAT in terms of accuracy, number of generations required for convergence, ability of performing feature selection and size of the evolved networks. For this purpose we employ artificial datasets of increasing complexity based on the exclusive-or (XOR) problem with irrelevant features.The di.erent initial topological se.ings are compared using Kruskal-Wallis hypothesis tests with Bonferroni correction (p<0.01), while FD-NEAT and FS-NEAT are compared using Wilcoxon rank sum hypothesis tests (p<0.01).The results show that the initial connectivity se.ing does not affect the performance of FD-NEAT and FS-NEAT.

Reference 
 
 
DOI  scopus