Special Statistical Properties of Neural Network

Abstract

| We elucidate essential diierences between feed-forward neural network models and conventional linear statistical models. When the target is overrealizable, the MLE of the former shows worse generalization, while experimental results reveals that iterative learning of a neural network shows eminent overtraining and better generalization in the middle.

Cite this paper

@inproceedings{Fukumizu1997SpecialSP, title={Special Statistical Properties of Neural Network}, author={Kenji Fukumizu}, year={1997} }