Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/5223
Title: Noise robustness in multilayer neural network
Authors: COPELLI LOPES DA SILVA, MAURO 
Eichhorn, R.
Kinouchi, O.
Biehl, M.
Simonetti, R.
Riegler, P.
Caticha, N.
Issue Date: 1997
Publisher: EDITIONS PHYSIQUE
Source: Europhysics letters, 37(6). p. 427-432
Abstract: The training of multilayered neural networks in the presence of different types of noise is studied. We consider the learning of realizable rules in nonoverlapping architectures. Achieving optimal generalization depends on the knowledge of the noise level, however its misestimation may lead to partial or complete loss of the generalization ability. We demonstrate this effect in the framework of online learning and present the results in terms of noise robustness phase diagrams. While for additive (weight) noise the robustness properties depend on the architecture and size of the networks, this is not so for multiplicative (output) noise. In this case we find a universal behaviour independent of the machine size for both the tree parity and committee machines.
Keywords: Statistical-Mechanics;Examples
Document URI: http://hdl.handle.net/1942/5223
DOI: 10.1209/epl/i1997-00167-2
ISI #: WOS:A1997WL76800009
Rights: Les Editions de Physique.
Category: A1
Type: Journal Contribution
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
_M._Copelli_1997_EPL_37_427.pdf901.27 kBAdobe PDFView/Open
Show full item record

SCOPUSTM   
Citations

8
checked on Sep 3, 2020

WEB OF SCIENCETM
Citations

10
checked on May 21, 2022

Page view(s)

8
checked on May 28, 2022

Download(s)

6
checked on May 28, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.