Multi-branch structure of layered neural networks

T. Yamashita, K. Hirasawa, Takayuki Furuzuki, J. Murata

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

9 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 languageEnglish
Title of host publicationICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages243-247
Number of pages5
Volume1
ISBN (Print)9810475241, 9789810475246
DOIs
Publication statusPublished - 2002
Externally publishedYes
Event9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
Duration: 2002 Nov 182002 Nov 22

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
CountrySingapore
CitySingapore
Period02/11/1802/11/22

Fingerprint

Neural networks
Explosions
Costs

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Yamashita, T., Hirasawa, K., Furuzuki, T., & Murata, J. (2002). Multi-branch structure of layered neural networks. In 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.; Furuzuki, Takayuki; Murata, J.

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.

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

Yamashita, T, Hirasawa, K, Furuzuki, T & Murata, J 2002, Multi-branch structure of layered neural networks. in 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, 02/11/18. https://doi.org/10.1109/ICONIP.2002.1202170
Yamashita T, Hirasawa K, Furuzuki T, Murata J. Multi-branch structure of layered neural networks. In 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. ; Furuzuki, Takayuki ; Murata, J. / 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. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2002. pp. 243-247
@inproceedings{34d48dfb638c48fca39674f339f7f0f2,
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 Takayuki Furuzuki and J. Murata",
year = "2002",
doi = "10.1109/ICONIP.2002.1202170",
language = "English",
isbn = "9810475241",
volume = "1",
pages = "243--247",
booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Multi-branch structure of layered neural networks

AU - Yamashita, T.

AU - Hirasawa, K.

AU - Furuzuki, Takayuki

AU - Murata, J.

PY - 2002

Y1 - 2002

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

SN - 9810475241

SN - 9789810475246

VL - 1

SP - 243

EP - 247

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

PB - Institute of Electrical and Electronics Engineers Inc.

ER -