mirage

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

DSpace/Manakin Repository

 

Search DR-NTU


Advanced Search Subject Search

Browse

My Account

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

Show full item record

Title: Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks.
Author: Wang, Lipo.
Copyright year: 1997
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.
Subject: DRNTU::Engineering::Electrical and electronic engineering.
Type: Journal Article
Series/ Journal Title: IEEE transactions on systems, man, and cybernetics – Part B: cybernetics
School: School of Electrical and Electronic Engineering
Rights: © 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].
Version: Accepted version

Files in this item

Files Size Format View
43. Noise injec ... ke-all neural networks.pdf 113.3Kb PDF View/Open
   

DOI Query

- Get published version (via Digital Object Identifier)
   

This item appears in the following Collection(s)

Show full item record

Statistics

Total views

All Items Views
Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks. 345

Total downloads

All Bitstreams Views
43. Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks.pdf 221

Top country downloads

Country Code Views
United States of America 92
Singapore 61
China 24
France 8
Unknown Country 4

Top city downloads

city Views
Mountain View 66
Singapore 61
Chongqing 11
Bangkok 3
Redwood City 3