Time of searching for similar binary vectors in associative memory
- 19 Downloads
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.
Keywordsassociative memory neural network Hopfield network binary vector indexing hashing
Unable to display preview. Download preview PDF.
- 3.D. O. Gorodnichi and A. M. Reznik, “Increasing attraction of pseudo-inverse autoassociative networks,” Neural Proces. Lett., 5(2), 123–127 (1997).Google Scholar
- 4.A. K. Dekhtyarenko and D. V. Novitskii, “Neural associative memory with cellular structure,” Mat. Mashiny i Sistemy, No. 3, 37–44 (2002).Google Scholar
- 5.A. A. Frolov, D. A. Rachkovskij, and D. Husek, “On information characteristics of Willshaw-like auto-associative memory,” Neural Network World, 2, 141–157 (2002).Google Scholar
- 6.D. A. Rachkovskii, I. S. Misuno, S. V. Slipchenko, and A. M. Sokolov, “Search for analogues with the help of distributed representations,” Problemy Programmirovaniya, No. 1, 39–50 (2005).Google Scholar
- 9.A. A. Frolov, D. Husek, and I. P. Muraviev, “Informational efficiency of sparsely encoded Hopfield-like associative memory,” Optical Memory & Neural Networks (Inform. Optics), 12(3), 177–197 (2004).Google Scholar
- 12.M. V. Tsodyks and M. V. Feigelman, “The enhanced storage capacity in neural network with low activity level,” Europhys. Lett., 6, 101–105 (1988).Google Scholar