Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks

Abstract—In this paper, we show that noise injection into inputs in un-supervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the Hopfield neural network, whereas the performance of a sparsely connected winner-take-all neural network does not depend on the injected training noise. I