Presentation 1994/12/16
Knowledge Processing using Multidirectional Associative Memory
Motonobu Hattori, Masafumi Hagiwara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper,we propose an associative memory based knowledge representaion network.The proposed network is composed of combined Multidirectional Associative Memories(MAMs).It has the following important abilities:inheritance,exceptions and robustness.As for the inheritance,the proposed network enables it from a superordinate concept to subordinate concepts by using a module which recalls is_a relation.Exceptional information processing is carried out by giving priority to subordinate concepts.In addition, the proposed network enables both many to many associations and difficult retrieval using Pseudo Noise(PN)patterns in training pairs.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) MAM / semantic networks / Pseudo Noise(PN)patterns / many to many association
Paper # NC94-57
Date of Issue

Conference Information
Committee NC
Conference Date 1994/12/16(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) Knowledge Processing using Multidirectional Associative Memory
Sub Title (in English)
Keyword(1) MAM
Keyword(2) semantic networks
Keyword(3) Pseudo Noise(PN)patterns
Keyword(4) many to many association
1st Author's Name Motonobu Hattori
1st Author's Affiliation Department of Electrical Engineering,Faculty of Science and Technology,Keio University()
2nd Author's Name Masafumi Hagiwara
2nd Author's Affiliation Department of Electrical Engineering,Faculty of Science and Technology,Keio University
Date 1994/12/16
Paper # NC94-57
Volume (vol) vol.94
Number (no) 417
Page pp.pp.-
#Pages 8
Date of Issue