Presentation 1993/6/19
A Binary Associative Memory with Multilayered Perceptrons
Chun-ying Ho, Shinsaku Mori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the paper,a multilayered associative memory that comprises only binary synapses is proposed.The network consists of two hidden layers which aim at achieving a better storage capacity and recall performances.A novel learning algorithm is then resented. The learning algorithm is capable of storing all the exemplar patterns as fixed points and of elimination most of the spurious states.Since the connection weights in the network are either 1 or -1,the proposed network exhibits a simple architecture that facilitates VLSI or ASIC implementation.Finally,the simulation results are shown to validate the efficiency of the network.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multilayered feedforward network / ASIC / VLSI / Spurions states / storage capacity
Paper # CAS93-44,NLP93-32
Date of Issue

Conference Information
Committee CAS
Conference Date 1993/6/19(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 Circuits and Systems (CAS)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Binary Associative Memory with Multilayered Perceptrons
Sub Title (in English)
Keyword(1) Multilayered feedforward network
Keyword(2) ASIC
Keyword(3) VLSI
Keyword(4) Spurions states
Keyword(5) storage capacity
1st Author's Name Chun-ying Ho
1st Author's Affiliation Department of Electrical Engineering,Faculty of Sciences and Technology,Keio University()
2nd Author's Name Shinsaku Mori
2nd Author's Affiliation Department of Electrical Engineering,Faculty of Sciences and Technology,Keio University
Date 1993/6/19
Paper # CAS93-44,NLP93-32
Volume (vol) vol.93
Number (no) 102
Page pp.pp.-
#Pages 6
Date of Issue