Neural associative memory for intelligent information processing

Motonobu Hattori, Masafumi Hagiwara

研究成果: Chapter

1 引用 (Scopus)

抄録

In this paper, first we derive a novel relaxation method for the system of linear inequalities and apply it to the learning for associative memories. Since the proposed intersection learning can guarantee the recall of all training data, it can greatly enlarge the storage capacity of associative memories. In addition, it requires much less weights renewal times than the conventional methods. We also propose a multimodule associative memory which can be learned by the intersection learning algorithm. The proposed associative memory can deal with many-to-many associations and it is applied to a knowledge processing task. Computer simulation results show the effectiveness of the proposed learning algorithm and associative memory.

元の言語English
ホスト出版物のタイトルInternational Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES
出版者IEEE
ページ377-386
ページ数10
2
出版物ステータスPublished - 1998
外部発表Yes
イベントProceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98) - Adelaide, Aust
継続期間: 1998 4 211998 4 23

Other

OtherProceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98)
Adelaide, Aust
期間98/4/2198/4/23

Fingerprint

Data storage equipment
Learning algorithms
Computer simulation
Processing

ASJC Scopus subject areas

  • Computer Science(all)

これを引用

Hattori, M., & Hagiwara, M. (1998). Neural associative memory for intelligent information processing. : International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES (巻 2, pp. 377-386). IEEE.

Neural associative memory for intelligent information processing. / Hattori, Motonobu; Hagiwara, Masafumi.

International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES. 巻 2 IEEE, 1998. p. 377-386.

研究成果: Chapter

Hattori, M & Hagiwara, M 1998, Neural associative memory for intelligent information processing. : International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES. 巻. 2, IEEE, pp. 377-386, Proceedings of the 1998 2nd International Conference on knowledge-Based Intelligent Electronic Systems (KES '98), Adelaide, Aust, 98/4/21.
Hattori M, Hagiwara M. Neural associative memory for intelligent information processing. : International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES. 巻 2. IEEE. 1998. p. 377-386
Hattori, Motonobu ; Hagiwara, Masafumi. / Neural associative memory for intelligent information processing. International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES. 巻 2 IEEE, 1998. pp. 377-386
@inbook{211e6bb39d95453bb381cdf62bb03f1a,
title = "Neural associative memory for intelligent information processing",
abstract = "In this paper, first we derive a novel relaxation method for the system of linear inequalities and apply it to the learning for associative memories. Since the proposed intersection learning can guarantee the recall of all training data, it can greatly enlarge the storage capacity of associative memories. In addition, it requires much less weights renewal times than the conventional methods. We also propose a multimodule associative memory which can be learned by the intersection learning algorithm. The proposed associative memory can deal with many-to-many associations and it is applied to a knowledge processing task. Computer simulation results show the effectiveness of the proposed learning algorithm and associative memory.",
author = "Motonobu Hattori and Masafumi Hagiwara",
year = "1998",
language = "English",
volume = "2",
pages = "377--386",
booktitle = "International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES",
publisher = "IEEE",

}

TY - CHAP

T1 - Neural associative memory for intelligent information processing

AU - Hattori, Motonobu

AU - Hagiwara, Masafumi

PY - 1998

Y1 - 1998

N2 - In this paper, first we derive a novel relaxation method for the system of linear inequalities and apply it to the learning for associative memories. Since the proposed intersection learning can guarantee the recall of all training data, it can greatly enlarge the storage capacity of associative memories. In addition, it requires much less weights renewal times than the conventional methods. We also propose a multimodule associative memory which can be learned by the intersection learning algorithm. The proposed associative memory can deal with many-to-many associations and it is applied to a knowledge processing task. Computer simulation results show the effectiveness of the proposed learning algorithm and associative memory.

AB - In this paper, first we derive a novel relaxation method for the system of linear inequalities and apply it to the learning for associative memories. Since the proposed intersection learning can guarantee the recall of all training data, it can greatly enlarge the storage capacity of associative memories. In addition, it requires much less weights renewal times than the conventional methods. We also propose a multimodule associative memory which can be learned by the intersection learning algorithm. The proposed associative memory can deal with many-to-many associations and it is applied to a knowledge processing task. Computer simulation results show the effectiveness of the proposed learning algorithm and associative memory.

UR - http://www.scopus.com/inward/record.url?scp=0032218785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032218785&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0032218785

VL - 2

SP - 377

EP - 386

BT - International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES

PB - IEEE

ER -