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

Section of Measurement and Control Engineering

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

10 Citations (Scopus)

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.

Original language	English
Title of host publication	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publication	Computational Intelligence for the E-Age
Editors	Jagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	243-247
Number of pages	5
Volume	1
ISBN (Electronic)	9810475241, 9789810475246
DOIs	https://doi.org/10.1109/ICONIP.2002.1202170
Publication status	Published - Jan 1 2002
Event	9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore Duration: Nov 18 2002 → Nov 22 2002

Other

Other	9th International Conference on Neural Information Processing, ICONIP 2002
Country	Singapore
City	Singapore
Period	11/18/02 → 11/22/02

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Access to Document

10.1109/ICONIP.2002.1202170

Fingerprint Dive into the research topics of 'Multi-branch structure of layered neural networks'. Together they form a unique fingerprint.

Cite this

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.

Research output: 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, Singapore, 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 -