Time of searching for similar binary vectors in associative memory |
| |
| Authors: | A. A. Frolov D. Husek D. A. Rachkovskii |
| |
| Affiliation: | (1) Institute of Higher Nervous Activity and Neurophysiology, Russian Academy of Sciences, Moscow, Russia;(2) Institute of Informatics, Academy of Sciences of the Czech Republic, Prague, Czechia;(3) International Scientific and Training Center of Information Technologies and Systems, National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Kiev, Ukraine |
| |
| Abstract: | Times of searching for similar binary vectors in neural-net and traditional associative memories are investigated and compared.
The neural-net approach is demonstrated to surpass the traditional ones even if it is implemented on a serial computer when
the entropy of a space of signals is of order of several hundreds and the number of stored vectors is vastly larger than the
entropy.
This work is supported by RFBR grant 05-07-90049 and partially by the Center of Applied Cybernetics under grant No. 1M6840070004
(Institutional Research Plan AV0Z10300504).
__________
Translated from Kibernetika i Sistemnyi Analiz, No. 5, pp. 3–13, September–October 2006. |
| |
| Keywords: | associative memory neural network Hopfield network binary vector indexing hashing |
| 本文献已被 SpringerLink 等数据库收录！ |
|
