Presentation 1996/3/18
A Proposal of Novel Knowledge Representation (Area Representation) and the Implementation by Neural Network
Naruhiro IKEDA, Masafumi HAGIWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, a novel knowledge representation method (area representation) and a novel neural network that realizes area representation are proposed. Area representation is a knowledge representation method for hierachical knolwedge that a superclass includes all the subclasses. The proposed network is based on two hypothesises. One is that a concept is recalled by excitation of a group of neurons in a brain. The other is that a knowledge is recollected by recall of some concepts. The network consists of several Kohonen Feature Maps, and organizes multidirectional associative memory. Computer simulation is carried out to confirm the validity of the proposed area representation and the network.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hierachical Knowledge / Area Representation / Kohonen Feature Map / Multidirectional Associative Memory
Paper # NC-95-145
Date of Issue

Conference Information
Committee NC
Conference Date 1996/3/18(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) A Proposal of Novel Knowledge Representation (Area Representation) and the Implementation by Neural Network
Sub Title (in English)
Keyword(1) Hierachical Knowledge
Keyword(2) Area Representation
Keyword(3) Kohonen Feature Map
Keyword(4) Multidirectional Associative Memory
1st Author's Name Naruhiro IKEDA
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 1996/3/18
Paper # NC-95-145
Volume (vol) vol.95
Number (no) 598
Page pp.pp.-
#Pages 8
Date of Issue