An Optimization Method of Layered Neural Networks based on the Modified Information Criterion

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Authors

Sumio Watanabe

Abstract

This paper proposes a practical optimization method for layered neural networks, by which the optimal model and parameter can be found simultaneously. 'i\Te modify the conventional information criterion into a differentiable function of parameters, and then, min(cid:173) imize it, while controlling it back to the ordinary form. Effective(cid:173) ness of this method is discussed theoretically and experimentally.