Distribution of the search of evolutionary product unit neural networks for classification

TL;DR

This paper explores distributed evolutionary algorithms for designing neural networks for classification, leveraging computer clusters to improve efficiency over traditional non-distributed methods.

Contribution

It introduces a distributed search approach for evolutionary product unit neural networks, enhancing design efficiency and reducing computational time.

Findings

Distributed search improves neural network design efficiency

Parallel processing reduces training time significantly

Effective architecture optimization using evolutionary algorithms

Abstract

This paper deals with the distributed processing in the search for an optimum classification model using evolutionary product unit neural networks. For this distributed search we used a cluster of computers. Our objective is to obtain a more efficient design than those net architectures which do not use a distributed process and which thus result in simpler designs. In order to get the best classification models we use evolutionary algorithms to train and design neural networks, which require a very time consuming computation. The reasons behind the need for this distribution are various. It is complicated to train this type of nets because of the difficulty entailed in determining their architecture due to the complex error surface. On the other hand, the use of evolutionary algorithms involves running a great number of tests with different seeds and parameters, thus resulting in a high computational cost