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

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...

Full description

Saved in:

Bibliographic Details
Main Author:	Wang, Lipo.
Other Authors:	School of Electrical and Electronic Engineering
Format:	Article
Language:	English
Published:	2012
Subjects:	DRNTU::Engineering::Electrical and electronic engineering
Online Access:	https://hdl.handle.net/10356/94091 http://hdl.handle.net/10220/8195
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-94091
record_format	dspace
spelling	sg-ntu-dr.10356-940912020-03-07T14:02:43Z Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks Wang, Lipo. School of Electrical and Electronic Engineering DRNTU::Engineering::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. Accepted version 2012-06-12T06:32:21Z 2019-12-06T18:50:29Z 2012-06-12T06:32:21Z 2019-12-06T18:50:29Z 1997 1997 Journal Article Wang, L. (1997). Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks. IEEE Transactions on Systems, Man, and Cybernetics – Part B: Cybernetics, 27(5), 868-870. https://hdl.handle.net/10356/94091 http://hdl.handle.net/10220/8195 10.1109/3477.623239 en 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]. 3 p. application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	DRNTU::Engineering::Electrical and electronic engineering
spellingShingle	DRNTU::Engineering::Electrical and electronic engineering Wang, Lipo. Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
description	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.
author2	School of Electrical and Electronic Engineering
author_facet	School of Electrical and Electronic Engineering Wang, Lipo.
format	Article
author	Wang, Lipo.
author_sort	Wang, Lipo.
title	Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
title_short	Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
title_full	Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
title_fullStr	Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
title_full_unstemmed	Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
title_sort	noise injection into inputs in sparsely connected hopfield and winner-take-all neural networks
publishDate	2012
url	https://hdl.handle.net/10356/94091 http://hdl.handle.net/10220/8195
_version_	1681046556816441344

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

Similar Items