Evolutionary Artificial Neural Network Based on Chemical Reaction Optimization

TL;DR

This paper introduces a novel approach using Chemical Reaction Optimization (CRO), a global optimization technique, to train artificial neural networks, demonstrating superior performance over traditional evolutionary algorithms.

Contribution

The paper presents the first application of CRO for training neural networks, replacing backpropagation and outperforming other evolutionary strategies.

Findings

CRO outperforms many existing EA strategies in training neural networks.

Simulation results validate the effectiveness of CRO in neural network optimization.

CRO demonstrates lower computational requirements compared to conventional methods.

Abstract

Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.