Scientific Research Publishing

Baum, E.B. and Haussler, D. (1989) What Size Net Gives Valid Generalization? Neural Information Processing Systems, 81-90.

ABSTRACT: With the boost of artificial intelligence, the study of neural network intrigues scientists. Artificial neural network, which was first designed theoretically in 1943 based on understanding ...
IEEE

Bayes statistical behavior and valid generalization of pattern classifying neural networks

Abstract: It is demonstrated both theoretically and experimentally that, under appropriate assumptions, a neural network pattern classifier implemented with a supervised learning algorithm generates ...
IEEE

Comments on "Bayes statistical behavior and valid generalization of pattern classifying neural networks" [with reply]

Abstract: In the above-titled paper (ibid., vol.2, p.471-475, July 1991), the authors claim that neural network classifiers duplicate the decision rule created by the empirical Bayes rule. The ...
GitHub

Generating Less Certain Adversarial Examples Improves Robust Generalization

This paper revisits the robust overfitting phenomenon of adversarial training. Observing that models with better robust generalization performance are less certain in predicting adversarially ...