Please use this identifier to cite or link to this item:
http://hdl.handle.net/10261/30523
Share/Export:
![]() ![]() |
|
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Title: | A deterministic algorithm that emulates learning with random weights |
Authors: | Ruiz de Angulo, Vicente CSIC ; Torras, Carme CSIC ORCID | Keywords: | Noise Noisy training Regularization Fault-tolerance Optimization Sensitivity Adaptive systems Automation |
Issue Date: | 2002 | Publisher: | Elsevier | Citation: | Neurocomputing 48(1): 975-1002 (2002) | Abstract: | The expectation of a function of random variables can be modeled as the value of the function in the mean value of the variables plus a penalty term. Here, this penalty term is calculated exactly, and the properties of different approximations are analyzed. Then, a deterministic algorithm for minimizing the expected error of a feedforward network of random weights is presented. Given a particular feedforward network architecture and a training set, this algorithm accurately finds the weight configuration that makes the network response most resistant to a class of weight perturbations. Finally, the study of the most stable configurations of a network unravels some undesirable properties of networks with asymmetric activation functions. | Publisher version (URL): | http://dx.doi.org/10.1016/S0925-2312(01)00695-6 | URI: | http://hdl.handle.net/10261/30523 | DOI: | 10.1016/S0925-2312(01)00695-6 | ISSN: | 0925-2312 |
Appears in Collections: | (IRII) Artículos |
Show full item record
Review this work
SCOPUSTM
Citations
3
checked on May 19, 2022
WEB OF SCIENCETM
Citations
2
checked on May 17, 2022
Page view(s)
331
checked on May 20, 2022
Download(s)
281
checked on May 20, 2022
Google ScholarTM
Check
Altmetric
Dimensions
WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.