Training neural networks with structured noise improves classification and generalization

The beneficial role of noise in learning is nowadays a consolidated concept in the field of artificial neural networks, suggesting that even biological systems might take advantage of similar mechanisms to maximize 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 are usually employed to model real neural systems. We show how adding structure into noisy training data can substantially improve the algorithm performance, allowing to approach perfect classification and maximal basins of attraction. We also prove that the so-called Hebbian unlearning rule coincides with the training-with-noise algorithm when noise is maximal and data are fixed points of the network dynamics. A sampling scheme for optimal noisy data is eventually proposed and implemented to outperform both the training-with-noise and the Hebbian unlearning procedures.