Uso de GSO cooperativos com decaimentos de pesos para otimizacao de redes neurais

TL;DR

This paper introduces hybrid cooperative Group Search Optimizer (GSO) algorithms with weight decay to enhance neural network training, demonstrating improved classification performance on benchmark datasets.

Contribution

The paper proposes two new hybrid cooperative GSO algorithms with weight decay, improving neural network optimization over traditional GSO methods.

Findings

Cooperative GSOs outperform traditional GSO in classification accuracy.

Hybrid approaches improve generalization with weight decay.

Effective on datasets like Cancer, Diabetes, Ecoli, and Glass.

Abstract

Training of Artificial Neural Networks is a complex task of great importance in supervised learning problems. Evolutionary Algorithms are widely used as global optimization techniques and these approaches have been used for Artificial Neural Networks to perform various tasks. An optimization algorithm, called Group Search Optimizer (GSO), was proposed and inspired by the search behaviour of animals. In this article we present two new hybrid approaches: CGSO-Hk-WD and CGSO-Sk-WD. Cooperative GSOs are based on the divide-and-conquer paradigm, employing cooperative behaviour between GSO groups to improve the performance of the standard GSO. We also apply the weight decay strategy (WD, acronym for Weight Decay) to increase the generalizability of the networks. The results show that cooperative GSOs are able to achieve better performance than traditional GSO for classification problems in benchmark datasets such as Cancer, Diabetes, Ecoli and Glass datasets.