Presentation 1994/6/28
Storage Capacity Analysis on a Model of Human Associative Processing,HASP
Masaki Kawamura, Yuzo Hirai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) While traditional associative memory models cannot resolve one- to-many associations,HASP can resolve such associations by mutually inhibitory networks.Since the mutually inhibitory networks can also eliminate crosstalk noise,the storage capacity of HASP will increase. In this paper,the storage capacity of HASP is analyzed.As the result of analysis,it is shown that when key and associative vectors are sparsely coded,storage capacity of HASP is more than twice the capacity of heteroassociative networks hitherto proposed. Since the number of connections of HASP is just twice the number of connections of heteroassociative networks,the performance overwhelms that of heteroassociative networks with the same number of connections as HASP.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) associative networks / crosstalk noise / Storage capacity / HASP
Paper # NC94-19
Date of Issue

Conference Information
Committee NC
Conference Date 1994/6/28(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) Storage Capacity Analysis on a Model of Human Associative Processing,HASP
Sub Title (in English)
Keyword(1) associative networks
Keyword(2) crosstalk noise
Keyword(3) Storage capacity
Keyword(4) HASP
1st Author's Name Masaki Kawamura
1st Author's Affiliation Master's Degree Program in Scientific Technology,University of Tsukuba()
2nd Author's Name Yuzo Hirai
2nd Author's Affiliation Institute of Information Sciences and Electronics,University of Tsukuba
Date 1994/6/28
Paper # NC94-19
Volume (vol) vol.94
Number (no) 129
Page pp.pp.-
#Pages 8
Date of Issue