Training neural networks with structured noise improves classification and generalization

arXiv:2302.13417v5 Announce Type: replace-cross
Abstract: The beneficial role of noise-injection in learning is a consolidated concept in the field of artificial neural networks, suggesting that even biological systems might take advantage of similar mechanisms to optimize their performance. The training-with-noise algorithm proposed by Gardner and collaborators is an emblematic example of a noise-injection procedure in recurrent networks, which can be used to model biological neural systems. We show how adding structure to noisy training data can substantially improve the algorithm …

abstract algorithm artificial artificial neural networks arxiv classification concept cond-mat.dis-nn cs.lg example networks neural networks noise performance role systems training type