A Novel Knowledge Representation (Area Representation) and Its Implementation by Neural Network

Naruhiro Ikeda, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

In this paper a new method of knowledge representation (area representation), and a new neural network based on it are proposed. Knowledge representation is the fundamental and important problem in the construction of an intelligent system. Local representation and distributed representation are typical examples but each has some merits and demerits. Area representation is intermediate between local and distributed representation and has the merits of both. The proposed novel neural network based on area representation uses the involution relation, where a lower-level concept is included in a higher-level concept and hierarchical-type representation of knowledge is possible. The network is formed by a number of Kohonen feature map layers that are coupled by a new learning algorithm known as neighborhood Hebbian learning, and as a whole, a multidirectional associative memory is constructed. The effectiveness of area representation and its implementation by neural networks are confirmed by computer simulation, where inheritance of knowledge from higher-level concept or recall from incomplete knowledge are investigated.

Original languageEnglish
Pages (from-to)34-42
Number of pages9
JournalSystems and Computers in Japan
Volume30
Issue number13
Publication statusPublished - 1999 Nov 30

Fingerprint

Knowledge representation
Knowledge Representation
Neural Networks
Neural networks
Intelligent systems
Hebbian Learning
Learning algorithms
Representation Type
Associative Memory
Intelligent Systems
Involution
Data storage equipment
Learning Algorithm
Computer Simulation
Computer simulation
Concepts
Knowledge

Keywords

  • Area representation
  • Knowledge with hierarchical structure
  • Kohonen feature map
  • Multidirectional associative memory

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science

Cite this

A Novel Knowledge Representation (Area Representation) and Its Implementation by Neural Network. / Ikeda, Naruhiro; Hagiwara, Masafumi.

In: Systems and Computers in Japan, Vol. 30, No. 13, 30.11.1999, p. 34-42.

Research output: Contribution to journalArticle

@article{1b71924ccfec455697c5cd2f528972b9,
title = "A Novel Knowledge Representation (Area Representation) and Its Implementation by Neural Network",
abstract = "In this paper a new method of knowledge representation (area representation), and a new neural network based on it are proposed. Knowledge representation is the fundamental and important problem in the construction of an intelligent system. Local representation and distributed representation are typical examples but each has some merits and demerits. Area representation is intermediate between local and distributed representation and has the merits of both. The proposed novel neural network based on area representation uses the involution relation, where a lower-level concept is included in a higher-level concept and hierarchical-type representation of knowledge is possible. The network is formed by a number of Kohonen feature map layers that are coupled by a new learning algorithm known as neighborhood Hebbian learning, and as a whole, a multidirectional associative memory is constructed. The effectiveness of area representation and its implementation by neural networks are confirmed by computer simulation, where inheritance of knowledge from higher-level concept or recall from incomplete knowledge are investigated.",
keywords = "Area representation, Knowledge with hierarchical structure, Kohonen feature map, Multidirectional associative memory",
author = "Naruhiro Ikeda and Masafumi Hagiwara",
year = "1999",
month = "11",
day = "30",
language = "English",
volume = "30",
pages = "34--42",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "13",

}

TY - JOUR

T1 - A Novel Knowledge Representation (Area Representation) and Its Implementation by Neural Network

AU - Ikeda, Naruhiro

AU - Hagiwara, Masafumi

PY - 1999/11/30

Y1 - 1999/11/30

N2 - In this paper a new method of knowledge representation (area representation), and a new neural network based on it are proposed. Knowledge representation is the fundamental and important problem in the construction of an intelligent system. Local representation and distributed representation are typical examples but each has some merits and demerits. Area representation is intermediate between local and distributed representation and has the merits of both. The proposed novel neural network based on area representation uses the involution relation, where a lower-level concept is included in a higher-level concept and hierarchical-type representation of knowledge is possible. The network is formed by a number of Kohonen feature map layers that are coupled by a new learning algorithm known as neighborhood Hebbian learning, and as a whole, a multidirectional associative memory is constructed. The effectiveness of area representation and its implementation by neural networks are confirmed by computer simulation, where inheritance of knowledge from higher-level concept or recall from incomplete knowledge are investigated.

AB - In this paper a new method of knowledge representation (area representation), and a new neural network based on it are proposed. Knowledge representation is the fundamental and important problem in the construction of an intelligent system. Local representation and distributed representation are typical examples but each has some merits and demerits. Area representation is intermediate between local and distributed representation and has the merits of both. The proposed novel neural network based on area representation uses the involution relation, where a lower-level concept is included in a higher-level concept and hierarchical-type representation of knowledge is possible. The network is formed by a number of Kohonen feature map layers that are coupled by a new learning algorithm known as neighborhood Hebbian learning, and as a whole, a multidirectional associative memory is constructed. The effectiveness of area representation and its implementation by neural networks are confirmed by computer simulation, where inheritance of knowledge from higher-level concept or recall from incomplete knowledge are investigated.

KW - Area representation

KW - Knowledge with hierarchical structure

KW - Kohonen feature map

KW - Multidirectional associative memory

UR - http://www.scopus.com/inward/record.url?scp=0346388751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0346388751&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0346388751

VL - 30

SP - 34

EP - 42

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 13

ER -