An evolutionary approach to training feedforward and recurrent neural networks

This paper describes a method of utilising genetic algorithms to train fixed architecture feedforward and recurrent neural networks. The technique described uses the genetic algorithm to evolve changes to the weights and biases of the network rather than the weights and biases themselves. Results achieved by this technique indicate that for many problems it compares very favourably with the more common gradient descent techniques for training neural networks, and in some cases is superior. The technique is useful for those problem which are known to be difficult for the gradient descent techniques.