Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
Date of Issue1997
School of Electrical and Electronic Engineering
In this paper, we show that noise injection into inputs in unsupervised 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.
DRNTU::Engineering::Electrical and electronic engineering
IEEE transactions on systems, man, and cybernetics – Part B: cybernetics
© 1997 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/3477.623239].