Comparing Hybrid Systems to Design and Optimize Artificial Neural Networks

Abstract. In this paper we conduct a comparative study between hybrid methods to optimize multilayer perceptrons: a model that optimizes the architecture and initial weights of multilayer perceptrons; a parallel approach to optimize the architecture and initial weights of multilayer perceptrons; a method that searches for the parameters of the training algorithm, and an approach for cooperative co-evolutionary optimization of multilayer perceptrons. Obtained results show that a co-evolutionary model obtains similar or better results than specialized approaches, needing much less training epochs and thus using much less simulation time.

• Type: Conference
• Year: 2004
• Where: EUROGP
• Authors: Pedro A. Castillo Valdivieso, Maribel García Arenas, Juan J. Merelo Guervós, Gustavo Romero, Fatima Rateb, Alberto Prieto
• Keywords: Cooperative Co-evolutionary Optimization, EUROGP 2004, Initial Weights, Multilayer Perceptrons, Optimization