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 | Size | Format | |
---|---|---|---|---|
_M._Copelli_1997_EPL_37_427.pdf | 901.27 kB | Adobe PDF | View/Open |
SCOPUSTM
Citations
8
checked on Sep 3, 2020
WEB OF SCIENCETM
Citations
13
checked on Sep 27, 2024
Page view(s)
46
checked on Nov 7, 2023
Download(s)
46
checked on Nov 7, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.