A Comparison Between ANN Generation and Training Methods and Their Development by Means of Graph Evolution: 2 Sample Problems

Daniel Rivero,Marcos Gestal,Juan R. Rabuñal,Julián Dorado

doi:10.1007/978-3-540-73007-1_12

A Comparison Between ANN Generation and Training Methods and Their Development by Means of Graph Evolution: 2 Sample Problems

Daniel Rivero, Marcos Gestal + Show 2 more

https://doi.org/10.1007/978-3-540-73007-1_12

Copy DOI

Publication Date: Jun 20, 2007

Citations: 14

Affiliation: University of A Coruña

#Artificial Neural Networks #Artificial Neural Networks Training Methods + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

This paper presents a study in which a new technique for automatically developing Artificial Neural Networks (ANNs) by means of Evolutionary Computation (EC) tools is compared with the traditional evolutionary techniques used for ANN development. The technique used here is based on network encoding on graphs and also their performance and evolution. For this comparison, 2 different real-world problems have been solved using various tools, and the results are presented here. According to them, the results obtained with this technique can beat those obtained with other ANN development tools.

Full Text