PREPROCESSING IN ATTRACTOR NEURAL NETWORKS

Authors
CARVALHAES CG COSTA AT PENNA TJP
Citation
Cg. Carvalhaes et al., PREPROCESSING IN ATTRACTOR NEURAL NETWORKS, International journal of modern physics C, 6(1), 1995, pp. 1-10
Citations number
28
Categorie Soggetti
Mathematical Method, Physical Science","Physycs, Mathematical","Computer Science Interdisciplinary Applications
Journal title
International journal of modern physics C → ACNP
ISSN journal
01291831
Volume
6
Issue
1
Year of publication
1995
Pages
1 - 10
Database
ISI
SICI code
0129-1831(1995)6:1<1:PIANN>2.0.ZU;2-B
Abstract
Preprocessing the input patterns seems the simplest approach to invari ant pattern recognition by neural networks. The Fourier transform has been proposed as an appropriate and elegant preprocessor. Nevertheless , we show in this work that the performance of this kind of preprocess or is strongly affected by the number of stored informations. This is so because the phase of the Fourier transform plays a more important r ole than the amplitude in the recognition process.