Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/18685
Title: Generalization transitions in Hidden-Layer neural networks for third-order feature discrimination
Author: Romeo Val, August
Keywords: Física estadística
Processos estocàstics
Biofísica
Statistical physics
Stochastic processes
Biophysics
Issue Date: 1993
Publisher: The American Physical Society
Abstract: Stochastic learning processes for a specific feature detector are studied. This technique is applied to nonsmooth multilayer neural networks requested to perform a discrimination task of order 3 based on the ssT-block¿ssC-block problem. Our system proves to be capable of achieving perfect generalization, after presenting finite numbers of examples, by undergoing a phase transition. The corresponding annealed theory, which involves the Ising model under external field, shows good agreement with Monte Carlo simulations.
Note: Reproducció del document publicat a: http://dx.doi.org/10.1103/PhysRevE.47.2162
It is part of: Physical Review E, 1993, vol. 47, núm. 3, p. 2162-2171
URI: http://hdl.handle.net/2445/18685
ISSN: 1063-651X
Appears in Collections:Articles publicats en revistes (Cognició, Desenvolupament i Psicologia de l'Educació)

Files in This Item:
File Description SizeFormat 
73475.pdf1.51 MBAdobe PDFView/Open


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