Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/3872
Title: DYNAMICS OF HIGHLY DILUTED NETWORKS OF CONTINUOUS NEURONS
Authors: JEDRZEJEWSKI, J
Komoda, A.
Issue Date: 1992
Publisher: EDITIONS PHYSIQUE
Source: EUROPHYSICS LETTERS, 18(3). p. 275-281
Abstract: We study the dynamics of the maximally stable network of analog neurons with a parallel update rule. For this type of network we determine the size of the basins of attraction and the effect of random destruction of synapses on the size of the basins of attraction and the attractor overlap. We present analytical and numerical results showing the significant increase of the wide retrieval regime in comparison with binary networks. On the other hand, we find that, in contradistinction to binary networks, our analog network fails to perform as an autoassociative memory if the percentage of cancelled synapses is larger than a certain critical value.
Notes: LIMBURGS UNIV CENTRUM,B-3590 DIEPENBEEK,BELGIUM.JEDRZEJEWSKI, J, WROCLAW UNIV,INST THEORET PHYS,CYBULSKIEGO 36,PL-50205 WROCLAW,POLAND.
Document URI: http://hdl.handle.net/1942/3872
ISI #: A1992HH05800015
Type: Journal Contribution
Appears in Collections:Non-affiliated authors

Show full item record

WEB OF SCIENCETM
Citations

1
checked on May 22, 2022

Page view(s)

64
checked on May 24, 2022

Google ScholarTM

Check


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