Multi-branch structure of layered neural networks

T. Yamashita; K. Hirasawa; Jinglu Hu; Junichi Murata

doi:10.1109/ICONIP.2002.1202170

Multi-branch structure of layered neural networks

T. Yamashita, K. Hirasawa, Jinglu Hu, Junichi Murata

計測制御工学

研究成果: Chapter in Book/Report/Conference proceeding › Conference contribution

10 被引用数 (Scopus)

抄録

In this paper, a multi-branch structure of neural networks is studied to make their size compact. The multi-branch structure has shown improved performance against conventional neural networks. As a result, it has been proved that the number of nodes of networks and the computational cost for training networks can be reduced. In addition, it could be said that proposed multi-branch networks are special cases of higher order neural networks, however, they obtain higher order effect easier without suffering the parameter explosion problem.

本文言語	英語
ホスト出版物のタイトル	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
ホスト出版物のサブタイトル	Computational Intelligence for the E-Age
編集者	Jagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee
出版社	Institute of Electrical and Electronics Engineers Inc.
ページ	243-247
ページ数	5
巻	1
ISBN（電子版）	9810475241, 9789810475246
DOI	https://doi.org/10.1109/ICONIP.2002.1202170
出版ステータス	出版済み - 1 1 2002
イベント	9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, シンガポール継続期間: 11 18 2002 → 11 22 2002

その他

その他	9th International Conference on Neural Information Processing, ICONIP 2002
国/地域	シンガポール
City	Singapore
Period	11/18/02 → 11/22/02

All Science Journal Classification (ASJC) codes

コンピュータネットワークおよび通信
情報システム
信号処理

文献へのアクセス

10.1109/ICONIP.2002.1202170

他のファイルとリンク

引用スタイル

Yamashita, T., Hirasawa, K., Hu, J., & Murata, J. (2002). Multi-branch structure of layered neural networks. In J. C. Rajapakse, X. Yao, L. Wang, K. Fukushima, & S-Y. Lee (Eds.), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (Vol. 1, pp. 243-247). [1202170] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1202170

Multi-branch structure of layered neural networks. / Yamashita, T.; Hirasawa, K.; Hu, Jinglu; Murata, Junichi.

ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. ed. / Jagath C. Rajapakse; Xin Yao; Lipo Wang; Kunihiko Fukushima; Soo-Young Lee. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2002. p. 243-247 1202170.

研究成果: Chapter in Book/Report/Conference proceeding › Conference contribution

Yamashita, T, Hirasawa, K, Hu, J & Murata, J 2002, Multi-branch structure of layered neural networks. in JC Rajapakse, X Yao, L Wang, K Fukushima & S-Y Lee (eds), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. vol. 1, 1202170, Institute of Electrical and Electronics Engineers Inc., pp. 243-247, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, シンガポール, 11/18/02. https://doi.org/10.1109/ICONIP.2002.1202170

Yamashita T, Hirasawa K, Hu J, Murata J. Multi-branch structure of layered neural networks. In Rajapakse JC, Yao X, Wang L, Fukushima K, Lee S-Y, editors, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Vol. 1. Institute of Electrical and Electronics Engineers Inc. 2002. p. 243-247. 1202170 https://doi.org/10.1109/ICONIP.2002.1202170

Yamashita, T. ; Hirasawa, K. ; Hu, Jinglu ; Murata, Junichi. / Multi-branch structure of layered neural networks. ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. editor / Jagath C. Rajapakse ; Xin Yao ; Lipo Wang ; Kunihiko Fukushima ; Soo-Young Lee. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2002. pp. 243-247

@inproceedings{05728b27af0f4d81b4a410f8b9821fdf,

title = "Multi-branch structure of layered neural networks",

abstract = "In this paper, a multi-branch structure of neural networks is studied to make their size compact. The multi-branch structure has shown improved performance against conventional neural networks. As a result, it has been proved that the number of nodes of networks and the computational cost for training networks can be reduced. In addition, it could be said that proposed multi-branch networks are special cases of higher order neural networks, however, they obtain higher order effect easier without suffering the parameter explosion problem.",

author = "T. Yamashita and K. Hirasawa and Jinglu Hu and Junichi Murata",

year = "2002",

month = jan,

day = "1",

doi = "10.1109/ICONIP.2002.1202170",

language = "English",

volume = "1",

pages = "243--247",

editor = "Rajapakse, {Jagath C.} and Xin Yao and Lipo Wang and Kunihiko Fukushima and Soo-Young Lee",

booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "9th International Conference on Neural Information Processing, ICONIP 2002 ; Conference date: 18-11-2002 Through 22-11-2002",

}

TY - GEN

T1 - Multi-branch structure of layered neural networks

AU - Yamashita, T.

AU - Hirasawa, K.

AU - Hu, Jinglu

AU - Murata, Junichi

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper, a multi-branch structure of neural networks is studied to make their size compact. The multi-branch structure has shown improved performance against conventional neural networks. As a result, it has been proved that the number of nodes of networks and the computational cost for training networks can be reduced. In addition, it could be said that proposed multi-branch networks are special cases of higher order neural networks, however, they obtain higher order effect easier without suffering the parameter explosion problem.

AB - In this paper, a multi-branch structure of neural networks is studied to make their size compact. The multi-branch structure has shown improved performance against conventional neural networks. As a result, it has been proved that the number of nodes of networks and the computational cost for training networks can be reduced. In addition, it could be said that proposed multi-branch networks are special cases of higher order neural networks, however, they obtain higher order effect easier without suffering the parameter explosion problem.

UR - http://www.scopus.com/inward/record.url?scp=84965053659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965053659&partnerID=8YFLogxK

U2 - 10.1109/ICONIP.2002.1202170

DO - 10.1109/ICONIP.2002.1202170

M3 - Conference contribution

AN - SCOPUS:84965053659

VL - 1

SP - 243

EP - 247

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing

A2 - Rajapakse, Jagath C.

A2 - Yao, Xin

A2 - Wang, Lipo

A2 - Fukushima, Kunihiko

A2 - Lee, Soo-Young

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Neural Information Processing, ICONIP 2002

Y2 - 18 November 2002 through 22 November 2002

ER -

Multi-branch structure of layered neural networks

抄録

その他

All Science Journal Classification (ASJC) codes

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル