New accelerated algorithm based on domain neural network for solving optimization tasks

Autor:	M. V. Kryzhanovskii, B. V. Kryzhanovskii, B. M. Magomedov
Rok vydání:	2007
Předmět:	Maxima and minima Optimization problem General Computer Science Artificial neural network Fictitious domain method Spins Domain model Electrical and Electronic Engineering Local field Algorithm Electronic Optical and Magnetic Materials Mathematics Domain (software engineering)
Zdroj:	Optical Memory and Neural Networks. 16:31-39
ISSN:	1934-7898 1060-992X
DOI:	10.3103/s1060992x07010043
Popis:	We propose a domain model of a neural network, in which individual spin-neurons are joined into larger-scale aggregates, the so-called domains. The updating rule in the domain model is defined by analogy with the usual spin dynamics: if the state of a domain in an inhomogeneous local field is unstable, then it flips, in the opposite case its state undergoes no changes. The number of stable states of the domain network grows linearly with the domain’s size k, where k is the number of spins in the domain. We show that the proposed model is effective for optimization problems, since the use of domain dynamics lowers the number of calculations in k 2 times and allows one to find deeper minima than the standard Hopfield model does.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4a460a852a001f7536e2ca3f69737f2f https://doi.org/10.3103/s1060992x07010043 Zobrazit plný text záznamu Full text from SpringerLink