Presentation 1995/7/27
Memory capacity and noise analysis of an associative memory using multiple inputs
Toshiaki Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Associative memory models are mainly classified as : auto-association, hetero-association, and temporal association. These models store one-to-one correspondence between memory patterns in their connection weights. So these models are able to recall a stored pattern from a noisy one. To extend this recalling capability of associative memory, a new model with a connection weight storing many-to-many correspondence is presented. This model recalls one pattern from an input pattern sequence which has a variety of pattern combinations. Bit error probabilities on a recalled pattern, memory capacity, and the noise effect are analysed in this report.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) associative memory / mamy-to-many / memory / capacity / sparse coding / neural network
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1995/7/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Memory capacity and noise analysis of an associative memory using multiple inputs
Sub Title (in English)
Keyword(1) associative memory
Keyword(2) mamy-to-many
Keyword(3) memory
Keyword(4) capacity
Keyword(5) sparse coding
Keyword(6) neural network
1st Author's Name Toshiaki Tanaka
1st Author's Affiliation Advanced Research Lab. Toshiba Corporation()
Date 1995/7/27
Paper #
Volume (vol) vol.95
Number (no) 189
Page pp.pp.-
#Pages 8
Date of Issue