Higher-order neural networks training using differential evolution
Michael G. Epitropakis, Vassilis P. Plagianakos, Michael N. Vrahatis · 2006
In this contribution, we study the class of Higher-Order Neural Networks, especially Pi-Sigma Networks. The performance of Pi-Sigma Networks is considered through well known neural network training problems. In our experiments, for the training process, we used Evolutionary Algorithms and more specifically the Differential Evolution algorithm. Preliminary results suggest that this training process is fast, stable and reliable and the trained Pi-Sigma network exhibited good generalization capabilities. 1