Self-organizing neural network for spatio-temporal patterns

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

1 Citation (Scopus)

Abstract

A self-organizing neural network for spatiotemporal patterns is proposed which is a nearest neighbor classifier that stores arbitrary-length spatiotemporal patterns. It has at least three layers. Layer-1 and layer-2 classify input spatial patterns one by one and the algorithm is based on the Carpenter/Grossberg net algorithm. Layer-2 and layer-3 classify and memorize the sequence of the patterns classified in layer-2. The connections between layer-2 and layer-3 are adjusted in both weight and time-delay to deal with spatiotemporal patterns. The features of the proposed neural network are its self-organization, classification, and memorization abilities for spatiotemporal patterns. In addition, it can distinguish different sequences composed of the same patterns such as 'ACT' and 'CAT' by unsupervised learning, and can deal with many sequences of different lengths.

Original languageEnglish
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages521-524
Number of pages4
ISBN (Print)0780301641
Publication statusPublished - 1992
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

Neural networks
Unsupervised learning
Time delay
Classifiers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hagiwara, M. (1992). Self-organizing neural network for spatio-temporal patterns. In Anon (Ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks (pp. 521-524). Publ by IEEE.

Self-organizing neural network for spatio-temporal patterns. / Hagiwara, Masafumi.

Proceedings. IJCNN - International Joint Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1992. p. 521-524.

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

Hagiwara, M 1992, Self-organizing neural network for spatio-temporal patterns. in Anon (ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE, pp. 521-524, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 91/7/8.
Hagiwara M. Self-organizing neural network for spatio-temporal patterns. In Anon, editor, Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE. 1992. p. 521-524
Hagiwara, Masafumi. / Self-organizing neural network for spatio-temporal patterns. Proceedings. IJCNN - International Joint Conference on Neural Networks. editor / Anon. Publ by IEEE, 1992. pp. 521-524
@inproceedings{7968e4d1e25744cbb0660776e9699910,
title = "Self-organizing neural network for spatio-temporal patterns",
abstract = "A self-organizing neural network for spatiotemporal patterns is proposed which is a nearest neighbor classifier that stores arbitrary-length spatiotemporal patterns. It has at least three layers. Layer-1 and layer-2 classify input spatial patterns one by one and the algorithm is based on the Carpenter/Grossberg net algorithm. Layer-2 and layer-3 classify and memorize the sequence of the patterns classified in layer-2. The connections between layer-2 and layer-3 are adjusted in both weight and time-delay to deal with spatiotemporal patterns. The features of the proposed neural network are its self-organization, classification, and memorization abilities for spatiotemporal patterns. In addition, it can distinguish different sequences composed of the same patterns such as 'ACT' and 'CAT' by unsupervised learning, and can deal with many sequences of different lengths.",
author = "Masafumi Hagiwara",
year = "1992",
language = "English",
isbn = "0780301641",
pages = "521--524",
editor = "Anon",
booktitle = "Proceedings. IJCNN - International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Self-organizing neural network for spatio-temporal patterns

AU - Hagiwara, Masafumi

PY - 1992

Y1 - 1992

N2 - A self-organizing neural network for spatiotemporal patterns is proposed which is a nearest neighbor classifier that stores arbitrary-length spatiotemporal patterns. It has at least three layers. Layer-1 and layer-2 classify input spatial patterns one by one and the algorithm is based on the Carpenter/Grossberg net algorithm. Layer-2 and layer-3 classify and memorize the sequence of the patterns classified in layer-2. The connections between layer-2 and layer-3 are adjusted in both weight and time-delay to deal with spatiotemporal patterns. The features of the proposed neural network are its self-organization, classification, and memorization abilities for spatiotemporal patterns. In addition, it can distinguish different sequences composed of the same patterns such as 'ACT' and 'CAT' by unsupervised learning, and can deal with many sequences of different lengths.

AB - A self-organizing neural network for spatiotemporal patterns is proposed which is a nearest neighbor classifier that stores arbitrary-length spatiotemporal patterns. It has at least three layers. Layer-1 and layer-2 classify input spatial patterns one by one and the algorithm is based on the Carpenter/Grossberg net algorithm. Layer-2 and layer-3 classify and memorize the sequence of the patterns classified in layer-2. The connections between layer-2 and layer-3 are adjusted in both weight and time-delay to deal with spatiotemporal patterns. The features of the proposed neural network are its self-organization, classification, and memorization abilities for spatiotemporal patterns. In addition, it can distinguish different sequences composed of the same patterns such as 'ACT' and 'CAT' by unsupervised learning, and can deal with many sequences of different lengths.

UR - http://www.scopus.com/inward/record.url?scp=0026732267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026732267&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026732267

SN - 0780301641

SP - 521

EP - 524

BT - Proceedings. IJCNN - International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -