LEARNING RULES FOR POTTS NEURAL NETWORKS WITH BIASED PATTERNS

Authors
BOLLE D VANHEMMEN JL HUYGHEBAERT J
Citation
D. Bolle et al., LEARNING RULES FOR POTTS NEURAL NETWORKS WITH BIASED PATTERNS, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics, 53(1), 1996, pp. 1276-1279
Citations number
15
Categorie Soggetti
Physycs, Mathematical","Phsycs, Fluid & Plasmas
Journal title
Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics → ACNP
ISSN journal
1063651X
Volume
53
Issue
1
Year of publication
1996
Part
B
Pages
1276 - 1279
Database
ISI
SICI code
1063-651X(1996)53:1<1276:LRFPNN>2.0.ZU;2-L
Abstract
We discuss appropriate modifications of the Hebbian learning rule for Q-state Potts neural networks with biased patterns, the purpose being to prevent the storage capacity from decreasing drastically with incre asing bias. Several prescriptions are compared. As an illustration the ir retrieval performance is studied numerically for Q = 3.