An experimental comparison of the Bayesian Ying-Yang criteria and cross validation for selection on number of hidden units in feedforward networks

Optimizing the number of hidden units in feedforward neural networks is an important issue in learning. Previously, a new criterion for selecting the number of hidden units in feedforward neural networks has been proposed by Xu (1997), based on the so-called Bayesian Ying-Yang (BYY) learning theory. The new criterion can be simply computed during the implementation of backpropagation training. In this paper, the criterion is experimentally studied and compared with the well-known cross validation approach. Simulation results show that obtained number of hidden units by the BYY criterion is highly consistent with the minimal generalization error and outperforms the cross validation approach