Distributed Evolutionary Computation using REST

TL;DR

This paper explores a distributed evolutionary computation framework using REST protocol, demonstrating that parallelization significantly reduces training time for multilayer perceptrons without sacrificing accuracy.

Contribution

It introduces a REST-based approach for distributed evolutionary optimization of neural networks, leveraging Perl, and shows effective speedup in training time.

Findings

Parallel version achieves similar or better results

Significant reduction in training time

Good speedup observed in experiments

Abstract

This paper analises distributed evolutionary computation based on the Representational State Transfer (REST) protocol, which overlays a farming model on evolutionary computation. An approach to evolutionary distributed optimisation of multilayer perceptrons (MLP) using REST and language Perl has been done. In these experiments, a master-slave based evolutionary algorithm (EA) has been implemented, where slave processes evaluate the costly fitness function (training a MLP to solve a classification problem). Obtained results show that the parallel version of the developed programs obtains similar or better results using much less time than the sequential version, obtaining a good speedup.