Uso de GSO cooperativos com decaimentos de pesos para otimizacao de redes neurais
This work addresses optimization challenges in neural network training for supervised learning, but it appears incremental as it builds on existing GSO methods with modifications.
The authors tackled the problem of training artificial neural networks by proposing two new hybrid approaches, CGSO-Hk-WD and CGSO-Sk-WD, which combine cooperative Group Search Optimizer (GSO) algorithms with weight decay strategies, resulting in improved performance over traditional GSO on benchmark classification datasets like Cancer, Diabetes, Ecoli, and Glass.
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.