Self-organizing multi-layer semantic maps

Hiroyuki Ichiki, Masafumi Hagiwara, Masao Nakagawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Self-organizing multilayer semantic maps are proposed. Three-layer models are simulated using two examples. Since the proposed networks are multilayer type, they can do higher-level information processing compared with the conventional minimal two-layer semantic maps. The computer simulation results indicate the effectiveness of the proposed maps. The maps can do hierarchical self-classification both in a self-organizing symbol map and in a role-based semantic map.

Original languageEnglish
Title of host publicationProceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages357-360
Number of pages4
ISBN (Print)0780301641
Publication statusPublished - 1991
Externally publishedYes
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: 1991 Jul 81991 Jul 12

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period91/7/891/7/12

Fingerprint

Semantics
Map symbols
Multilayers
Computer simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ichiki, H., Hagiwara, M., & Nakagawa, M. (1991). Self-organizing multi-layer semantic maps. In Anon (Ed.), Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks (pp. 357-360). Publ by IEEE.

Self-organizing multi-layer semantic maps. / Ichiki, Hiroyuki; Hagiwara, Masafumi; Nakagawa, Masao.

Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1991. p. 357-360.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ichiki, H, Hagiwara, M & Nakagawa, M 1991, Self-organizing multi-layer semantic maps. in Anon (ed.), Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks. Publ by IEEE, pp. 357-360, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 91/7/8.
Ichiki H, Hagiwara M, Nakagawa M. Self-organizing multi-layer semantic maps. In Anon, editor, Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks. Publ by IEEE. 1991. p. 357-360
Ichiki, Hiroyuki ; Hagiwara, Masafumi ; Nakagawa, Masao. / Self-organizing multi-layer semantic maps. Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks. editor / Anon. Publ by IEEE, 1991. pp. 357-360
@inproceedings{4ca75767b1484ee190dfa872569d16e6,
title = "Self-organizing multi-layer semantic maps",
abstract = "Self-organizing multilayer semantic maps are proposed. Three-layer models are simulated using two examples. Since the proposed networks are multilayer type, they can do higher-level information processing compared with the conventional minimal two-layer semantic maps. The computer simulation results indicate the effectiveness of the proposed maps. The maps can do hierarchical self-classification both in a self-organizing symbol map and in a role-based semantic map.",
author = "Hiroyuki Ichiki and Masafumi Hagiwara and Masao Nakagawa",
year = "1991",
language = "English",
isbn = "0780301641",
pages = "357--360",
editor = "Anon",
booktitle = "Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Self-organizing multi-layer semantic maps

AU - Ichiki, Hiroyuki

AU - Hagiwara, Masafumi

AU - Nakagawa, Masao

PY - 1991

Y1 - 1991

N2 - Self-organizing multilayer semantic maps are proposed. Three-layer models are simulated using two examples. Since the proposed networks are multilayer type, they can do higher-level information processing compared with the conventional minimal two-layer semantic maps. The computer simulation results indicate the effectiveness of the proposed maps. The maps can do hierarchical self-classification both in a self-organizing symbol map and in a role-based semantic map.

AB - Self-organizing multilayer semantic maps are proposed. Three-layer models are simulated using two examples. Since the proposed networks are multilayer type, they can do higher-level information processing compared with the conventional minimal two-layer semantic maps. The computer simulation results indicate the effectiveness of the proposed maps. The maps can do hierarchical self-classification both in a self-organizing symbol map and in a role-based semantic map.

UR - http://www.scopus.com/inward/record.url?scp=0026391855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026391855&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026391855

SN - 0780301641

SP - 357

EP - 360

BT - Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -