Extracted memory from temporal patterns using adaptive resonance and recurrent network

Osamu Araki

Extracted memory from temporal patterns using adaptive resonance and recurrent network

Department of Applied Physics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We can recognize objects through receiving continuously huge temporal information including redundancy and noise, and can memorize them. This paper proposes a neural network model which extracts pre-recognized patterns from temporally sequential patterns which include redundancy, and memorizes the patterns temporarily. This model consists of an adaptive resonance system and a recurrent time-delay network. The extraction is executed by the matching mechanism of the adaptive resonance system, and the temporal information is processed and stored by the recurrent network. Simple simulations are examined to exemplify the property of extraction.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Publisher	Publ by IEEE
Pages	2642-2645
Number of pages	4
ISBN (Print)	0780314212, 9780780314214
Publication status	Published - 1993
Event	Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn Duration: 25 Oct 1993 → 29 Oct 1993

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	3

Conference

Conference	Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
City	Nagoya, Jpn
Period	25/10/93 → 29/10/93

Cite this

@inproceedings{e890d7d64c0e463c82b57c130820e12a,

title = "Extracted memory from temporal patterns using adaptive resonance and recurrent network",

abstract = "We can recognize objects through receiving continuously huge temporal information including redundancy and noise, and can memorize them. This paper proposes a neural network model which extracts pre-recognized patterns from temporally sequential patterns which include redundancy, and memorizes the patterns temporarily. This model consists of an adaptive resonance system and a recurrent time-delay network. The extraction is executed by the matching mechanism of the adaptive resonance system, and the temporal information is processed and stored by the recurrent network. Simple simulations are examined to exemplify the property of extraction.",

author = "Osamu Araki",

year = "1993",

language = "English",

isbn = "0780314212",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Publ by IEEE",

pages = "2642--2645",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) ; Conference date: 25-10-1993 Through 29-10-1993",

}

Araki, O 1993, Extracted memory from temporal patterns using adaptive resonance and recurrent network. in Proceedings of the International Joint Conference on Neural Networks. Proceedings of the International Joint Conference on Neural Networks, vol. 3, Publ by IEEE, pp. 2642-2645, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 25/10/93.

Extracted memory from temporal patterns using adaptive resonance and recurrent network. / Araki, Osamu.
Proceedings of the International Joint Conference on Neural Networks. Publ by IEEE, 1993. p. 2642-2645 (Proceedings of the International Joint Conference on Neural Networks; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Extracted memory from temporal patterns using adaptive resonance and recurrent network

AU - Araki, Osamu

PY - 1993

Y1 - 1993

N2 - We can recognize objects through receiving continuously huge temporal information including redundancy and noise, and can memorize them. This paper proposes a neural network model which extracts pre-recognized patterns from temporally sequential patterns which include redundancy, and memorizes the patterns temporarily. This model consists of an adaptive resonance system and a recurrent time-delay network. The extraction is executed by the matching mechanism of the adaptive resonance system, and the temporal information is processed and stored by the recurrent network. Simple simulations are examined to exemplify the property of extraction.

AB - We can recognize objects through receiving continuously huge temporal information including redundancy and noise, and can memorize them. This paper proposes a neural network model which extracts pre-recognized patterns from temporally sequential patterns which include redundancy, and memorizes the patterns temporarily. This model consists of an adaptive resonance system and a recurrent time-delay network. The extraction is executed by the matching mechanism of the adaptive resonance system, and the temporal information is processed and stored by the recurrent network. Simple simulations are examined to exemplify the property of extraction.

UR - https://www.scopus.com/pages/publications/0027809813

M3 - Conference contribution

AN - SCOPUS:0027809813

SN - 0780314212

SN - 9780780314214

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 2642

EP - 2645

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

T2 - Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)

Y2 - 25 October 1993 through 29 October 1993

ER -

Extracted memory from temporal patterns using adaptive resonance and recurrent network

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this