Multi-branch structure and its localized property in layered neural networks

Takashi Yamashita, Kotaro Hirasawa, Takayuki Furuzuki

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

4 Citations (Scopus)

Abstract

Neural networks (NNs) can solve only a simple problem if the network size is too compact, on the other hand, if the network size increases, it costs a lot in terms of calculation time. So, we have studied how to construct the network structure with high performances and low costs in space and time. A solution is a multi-branch structure. Conventional NNs uses the single-branch for the connections, while the multi-branch structure has multi-branches between the nodes. In this paper, a new method which enable the multi-branch NNs to have localized property is proposed. It is well known that RBF networks have localized property that makes it possible to approximate functions faster than signioidal NNs. By using the multi-branch structure having localized property, NNs could obtain high performances keeping the lower costs in space and time. Simulation results of function approximations and classification problems illustrated the effectiveness of multi-branch NNs.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages1039-1044
Number of pages6
Volume2
DOIs
Publication statusPublished - 2004
Event2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest
Duration: 2004 Jul 252004 Jul 29

Other

Other2004 IEEE International Joint Conference on Neural Networks - Proceedings
CityBudapest
Period04/7/2504/7/29

Fingerprint

Neural networks
Costs
Radial basis function networks

ASJC Scopus subject areas

  • Software

Cite this

Yamashita, T., Hirasawa, K., & Furuzuki, T. (2004). Multi-branch structure and its localized property in layered neural networks. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 2, pp. 1039-1044) https://doi.org/10.1109/IJCNN.2004.1380077

Multi-branch structure and its localized property in layered neural networks. / Yamashita, Takashi; Hirasawa, Kotaro; Furuzuki, Takayuki.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 2004. p. 1039-1044.

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

Yamashita, T, Hirasawa, K & Furuzuki, T 2004, Multi-branch structure and its localized property in layered neural networks. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, pp. 1039-1044, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, 04/7/25. https://doi.org/10.1109/IJCNN.2004.1380077
Yamashita T, Hirasawa K, Furuzuki T. Multi-branch structure and its localized property in layered neural networks. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2. 2004. p. 1039-1044 https://doi.org/10.1109/IJCNN.2004.1380077
Yamashita, Takashi ; Hirasawa, Kotaro ; Furuzuki, Takayuki. / Multi-branch structure and its localized property in layered neural networks. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 2004. pp. 1039-1044
@inproceedings{a3aec903d06648c1bbfc416084637142,
title = "Multi-branch structure and its localized property in layered neural networks",
abstract = "Neural networks (NNs) can solve only a simple problem if the network size is too compact, on the other hand, if the network size increases, it costs a lot in terms of calculation time. So, we have studied how to construct the network structure with high performances and low costs in space and time. A solution is a multi-branch structure. Conventional NNs uses the single-branch for the connections, while the multi-branch structure has multi-branches between the nodes. In this paper, a new method which enable the multi-branch NNs to have localized property is proposed. It is well known that RBF networks have localized property that makes it possible to approximate functions faster than signioidal NNs. By using the multi-branch structure having localized property, NNs could obtain high performances keeping the lower costs in space and time. Simulation results of function approximations and classification problems illustrated the effectiveness of multi-branch NNs.",
author = "Takashi Yamashita and Kotaro Hirasawa and Takayuki Furuzuki",
year = "2004",
doi = "10.1109/IJCNN.2004.1380077",
language = "English",
isbn = "0780383591",
volume = "2",
pages = "1039--1044",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - Multi-branch structure and its localized property in layered neural networks

AU - Yamashita, Takashi

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

PY - 2004

Y1 - 2004

N2 - Neural networks (NNs) can solve only a simple problem if the network size is too compact, on the other hand, if the network size increases, it costs a lot in terms of calculation time. So, we have studied how to construct the network structure with high performances and low costs in space and time. A solution is a multi-branch structure. Conventional NNs uses the single-branch for the connections, while the multi-branch structure has multi-branches between the nodes. In this paper, a new method which enable the multi-branch NNs to have localized property is proposed. It is well known that RBF networks have localized property that makes it possible to approximate functions faster than signioidal NNs. By using the multi-branch structure having localized property, NNs could obtain high performances keeping the lower costs in space and time. Simulation results of function approximations and classification problems illustrated the effectiveness of multi-branch NNs.

AB - Neural networks (NNs) can solve only a simple problem if the network size is too compact, on the other hand, if the network size increases, it costs a lot in terms of calculation time. So, we have studied how to construct the network structure with high performances and low costs in space and time. A solution is a multi-branch structure. Conventional NNs uses the single-branch for the connections, while the multi-branch structure has multi-branches between the nodes. In this paper, a new method which enable the multi-branch NNs to have localized property is proposed. It is well known that RBF networks have localized property that makes it possible to approximate functions faster than signioidal NNs. By using the multi-branch structure having localized property, NNs could obtain high performances keeping the lower costs in space and time. Simulation results of function approximations and classification problems illustrated the effectiveness of multi-branch NNs.

UR - http://www.scopus.com/inward/record.url?scp=10944243766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10944243766&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2004.1380077

DO - 10.1109/IJCNN.2004.1380077

M3 - Conference contribution

AN - SCOPUS:10944243766

SN - 0780383591

VL - 2

SP - 1039

EP - 1044

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -