Nonlinear Factorization in Hopfield-like Neural Networks

0404560 - UIVT-O 20010177 RIV SK eng C - Conference Paper (international conference)
Frolov, A. A. - Húsek, Dušan - Snášel, V. - Sirota, A.M.
Nonlinear Factorization in Hopfield-like Neural Networks.
Digital Signal Processing and Multimedia Communications. Košice: Mercury Smékal Publishing House, 2001 - (Lukáč, R.; Galajda, P.; Marchevský, S.; Drutarovský, M.), s. 98-101. ISBN 80-89061-49-4.
[DSP-MCOM 2001. International Scientific Conference /5./. Košice (SK), 27.11.2001-29.11.2001]
R&D Projects: GA ČR GA201/01/1192; GA ČR GA201/00/1031
Institutional research plan: AV0Z1030915
Keywords : binary factorization * Hopfield network * sparse encoding
Subject RIV: BB - Applied Statistics, Operational Research

The problem in binary factorization of complex patterns in recurrent Hopfield-like neural network was studied by means of computer simulation. The network ability to perform a factorization was analyzed depending on the number and sparseness of factors mixed in presented patterns. Binary factorization in sparsely encoded Hopfield-like neural network is treated as efficient statistical method and as a functional model of hippocampal CA3 field.
Permanent Link: http://hdl.handle.net/11104/0124808