Retrieval and chaos in extremely dilutedQ-Ising neural networks

Autor:	B Vinck, Va Zagrebnov, Désiré Bollé, Gyoung Moo Shim
Rok vydání:	1994
Předmět:	CHAOS (operating system) Artificial neural network Time evolution Chaotic Probabilistic logic Recursion (computer science) Parallel dynamics Statistical and Nonlinear Physics Ising model Statistical physics Algorithm Mathematical Physics Mathematics
Zdroj:	Journal of Statistical Physics. 74:565-582
ISSN:	1572-9613 0022-4715
DOI:	10.1007/bf02188571
Popis:	Using a probabilistic approach, the deterministic and the stochastic parallel dynamics of aQ-Ising neural network are studied at finiteQ and in the limitQ→∞. Exact evolution equations are presented for the first time-step. These formulas constitute recursion relations for the parallel dynamics of the extremely diluted asymmetric versions of these networks. An explicit analysis of the retrieval properties is carried out in terms of the gain parameter, the loading capacity, and the temperature. The results for theQ→∞ network are compared with those for theQ=3 andQ=4 models. Possible chaotic microscopic behavior is studied using the time evolution of the distance between two network configurations. For arbitrary finiteQ the retrieval regime is always chaotic. In the limitQ→∞ the network exhibits a dynamical transition toward chaos.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fbf1cebd2778a36549f1ab710fe803de https://doi.org/10.1007/bf02188571 Zobrazit plný text záznamu Full text from SpringerLink