Familiarity recognition and recollection: A neural network model

Autor:	A. T. Terekhin, E. V. Budilova, L. M. Kachalova, M. P. Karpenko
Rok vydání:	2009
Předmět:	Hopfield network Artificial neural network Time delay neural network business.industry Product (mathematics) Biophysics Scalar (physics) Pattern recognition Artificial intelligence Function (mathematics) business Image (mathematics) Sign (mathematics)
Zdroj:	Biophysics. 54:349-354
ISSN:	1555-6654 0006-3509
Popis:	The capacities of a specially designed neural network for familiarity recognition and recollection have been compared. Recognition is based on calculating “image familiarity” as a modified Hopfield energy function in which the value of the inner sum is replaced by the sign of this value. This replacement makes the calculation of familiarity compatible with the basic dynamic equations of the Hopfield network and is in fact reduced to calculating the scalar product of the neuronet state vectors at two successive time steps.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::2da810adc1786a168135de9d142d4893 https://doi.org/10.1134/s0006350909030178 Zobrazit plný text záznamu Full text from SpringerLink