DocumentCode
1553586
Title
Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
Author
Wang, Lipo
Author_Institution
Sch. of Comput. & Math., Deakin Univ., Clayton, Vic., Australia
Volume
27
Issue
5
fYear
1997
fDate
9/1/1997 12:00:00 AM
Firstpage
868
Lastpage
870
Abstract
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
Keywords
Hopfield neural nets; noise; unsupervised learning; Hopfield neural network; injected training noise; neural networks; sparsely connected; unsupervised learning; winner-take-all neural network; Active noise reduction; Artificial neural networks; Degradation; Hopfield neural networks; Intelligent networks; Neural networks; Neurons; Signal processing; Supervised learning; Unsupervised learning;
fLanguage
English
Journal_Title
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
Publisher
ieee
ISSN
1083-4419
Type
jour
DOI
10.1109/3477.623239
Filename
623239
Link To Document