Hopfield neural networks for state estimation: parameters, efficient implementation and results

Autor:	Francisco Sandoval, Francisco García-Lagos, F. J. Marín, Gonzalo Joya
Rok vydání:	2000
Předmět:	Hopfield network Probabilistic neural network Mathematical optimization Recurrent neural network Optimization problem Artificial neural network Computer science Time delay neural network State vector Electrical and Electronic Engineering Types of artificial neural networks
Zdroj:	e & i Elektrotechnik und Informationstechnik. 117:4-7
ISSN:	1613-7620 0932-383X
Popis:	State estimation processes measurements and other information to find the network state vector. In this paper, state estimation is considered as an optimization problem to be solved with a Hopfield neural network. Several activation models for this network are simulated and compared. A new method is proposed that calculates the integration step parameter for this network in an autonomous way, eliminating the need for determining it in a manual way for each particular problem. This algorithm has been successfully tested for a wide range of electrical nets. Neural and classic analytical methods are compared.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::ada1baacec43d9ecb09bcadf2c45ef97 https://doi.org/10.1007/bf03161391 Zobrazit plný text záznamu Full text from SpringerLink