On the parallel dynamics of theQ-state Potts andQ-Ising neural networks

Autor:	B Vinck, Va Zagrebnov, Désiré Bollé
Rok vydání:	1993
Předmět:	Combinatorics Artificial neural network Parallel processing (DSP implementation) Mathematical model Zero (complex analysis) Recursion (computer science) Statistical and Nonlinear Physics Ising model Statistical physics Absolute zero Mathematical Physics Potts model Mathematics
Zdroj:	Journal of Statistical Physics. 70:1099-1119
ISSN:	1572-9613 0022-4715
DOI:	10.1007/bf01049424
Popis:	Using a probabilistic approach, the parallel dynamics of theQ-state Potts andQ-Ising neural networks are studied at zero and at nonzero temperatures. Evolution equations are derived for the first time step and arbitraryQ. These formulas constitute recursion relations for the exact parallel dynamics of the extremely diluted asymmetric versions of these networks. An explicit analysis, including dynamical capacity-temperature diagrams and the temperature dependence of the overlap, is carried out forQ=3. Both types of models are compared.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8bdf6127c98dd07082af2303c7c6f87a https://doi.org/10.1007/bf01049424 Zobrazit plný text záznamu Full text from SpringerLink