Recall Time in Densely Encoded Hopfield Network: Results from KFS Theory and Computer Simulation

0404195 - UIVT-O 20010056 RIV AT eng C - Konferenční příspěvek (zahraniční konf.)
Frolov, A. A. - Húsek, Dušan - Combe, P. - Snášel, V.
Recall Time in Densely Encoded Hopfield Network: Results from KFS Theory and Computer Simulation.
Artificial Neural Nets and Genetic Algorithms. Proceedings of the International conference. Wien: Springer, 2001 - (Kůrková, V.; Steele, N.; Neruda, R.; Kárný, M.), s. 74-77. ISBN 3-211-83651-9.
[ICANNGA'2001 /5./. Praha (CZ), 22.04.2001-25.04.2001]
Grant CEP: GA ČR GA201/01/1192; GA ČR GA201/00/1031
Grant ostatní: BARRANDE(XE) 99010-2
Výzkumný záměr: AV0Z1030915
Klíčová slova: recall time * Hopfield networks * neural networks * parallel dynamics
Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum

Recall time in densely encoded Hopfield neural network with parallel dynamics is investigated analytically and by computer simulation. The method of the recall time estimation is based on calculation of overlaps between successive patterns of network dynamics. It is shown that this time actually gives rather accurate estimate for the recall time and that the overlap between successive patterns of network dynamics can be rather accurately estimated by the theory recently developed by Koyama et al.
Trvalý link: http://hdl.handle.net/11104/0124462