Global Optimization Methods for Designing and Training Feedforward Artificial Neural Networks

This paper presents a new method that integrates tabu search, simulated annealing, genetic algorithms and backpropagation in both a pruning and constructive manner. The approach obtained promising results in the simultaneous optimization of an artificial neural network architecture and weights. With the proposed method, we investigate four cost functions for global optimization methods: the average method, weight-decay, multi-objective optimization and combined multiobjective/weight-decay. The experiments are performed in four classifications and one prediction problem.