www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

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, M.
Eichhorn, R.
Kinouchi, O.
Biehl, M.
Simonetti, R.
Riegler, P.
Caticha, N.
Issue Date: 1997
Citation: 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.
URI: http://hdl.handle.net/1942/5223
DOI: 10.1209/epl/i1997-00167-2
Type: Journal Contribution
Appears in Collections: Research publications

Files in This Item:

There are no files associated with this item.

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