Training artificial neural networks using Taguchi methods

This paper shows how the process optimization methods known as Taguchi meth ods may be applied to the training of Artificial Neural Networks. A compari son is made between the efficiency of training using Taguchi methods and th e efficiency of conventional training methods; attention is drawn to the ad vantages of Taguchi methods. Further, it is shown that Taguchi methods offe r potential benefits in evaluating network behaviour such as the ability to examine interaction of weights and neurons within a network.