A study of functions distribution of neural networks

Q. Xiong, K. Hirasawa, Takayuki Furuzuki, J. Murata

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

Abstract

In this paper, Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR) is studied, which consists of basic networks and branch control networks. The branch control network can be used to determine which intermediate nodes of the basic network should be connected to the output node with a coefficient of relative strength ranging from zero to one. This determination will adjust the outputs of the intermediate nodes of the basic network. Therefore, by using ULNs with BC, locally functions distributed networks can be realized depending on the values of the inputs of the network. ULNs with BR is applied to a two-spirals problem. The simulation results show that ULNs with BC exhibits better performance than the conventional networks with comparable complexity.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages2361-2367
Number of pages7
Volume4
Publication statusPublished - 2001
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC
Duration: 2001 Jul 152001 Jul 19

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'01)
CityWashington, DC
Period01/7/1501/7/19

Fingerprint

Distribution functions
Neural networks

ASJC Scopus subject areas

  • Software

Cite this

Xiong, Q., Hirasawa, K., Furuzuki, T., & Murata, J. (2001). A study of functions distribution of neural networks. In Proceedings of the International Joint Conference on Neural Networks (Vol. 4, pp. 2361-2367)

A study of functions distribution of neural networks. / Xiong, Q.; Hirasawa, K.; Furuzuki, Takayuki; Murata, J.

Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. p. 2361-2367.

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

Xiong, Q, Hirasawa, K, Furuzuki, T & Murata, J 2001, A study of functions distribution of neural networks. in Proceedings of the International Joint Conference on Neural Networks. vol. 4, pp. 2361-2367, International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, 01/7/15.
Xiong Q, Hirasawa K, Furuzuki T, Murata J. A study of functions distribution of neural networks. In Proceedings of the International Joint Conference on Neural Networks. Vol. 4. 2001. p. 2361-2367
Xiong, Q. ; Hirasawa, K. ; Furuzuki, Takayuki ; Murata, J. / A study of functions distribution of neural networks. Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. pp. 2361-2367
@inproceedings{6671a6f57c3d428d9a573b121fc01698,
title = "A study of functions distribution of neural networks",
abstract = "In this paper, Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR) is studied, which consists of basic networks and branch control networks. The branch control network can be used to determine which intermediate nodes of the basic network should be connected to the output node with a coefficient of relative strength ranging from zero to one. This determination will adjust the outputs of the intermediate nodes of the basic network. Therefore, by using ULNs with BC, locally functions distributed networks can be realized depending on the values of the inputs of the network. ULNs with BR is applied to a two-spirals problem. The simulation results show that ULNs with BC exhibits better performance than the conventional networks with comparable complexity.",
author = "Q. Xiong and K. Hirasawa and Takayuki Furuzuki and J. Murata",
year = "2001",
language = "English",
volume = "4",
pages = "2361--2367",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - A study of functions distribution of neural networks

AU - Xiong, Q.

AU - Hirasawa, K.

AU - Furuzuki, Takayuki

AU - Murata, J.

PY - 2001

Y1 - 2001

N2 - In this paper, Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR) is studied, which consists of basic networks and branch control networks. The branch control network can be used to determine which intermediate nodes of the basic network should be connected to the output node with a coefficient of relative strength ranging from zero to one. This determination will adjust the outputs of the intermediate nodes of the basic network. Therefore, by using ULNs with BC, locally functions distributed networks can be realized depending on the values of the inputs of the network. ULNs with BR is applied to a two-spirals problem. The simulation results show that ULNs with BC exhibits better performance than the conventional networks with comparable complexity.

AB - In this paper, Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR) is studied, which consists of basic networks and branch control networks. The branch control network can be used to determine which intermediate nodes of the basic network should be connected to the output node with a coefficient of relative strength ranging from zero to one. This determination will adjust the outputs of the intermediate nodes of the basic network. Therefore, by using ULNs with BC, locally functions distributed networks can be realized depending on the values of the inputs of the network. ULNs with BR is applied to a two-spirals problem. The simulation results show that ULNs with BC exhibits better performance than the conventional networks with comparable complexity.

UR - http://www.scopus.com/inward/record.url?scp=0034860789&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034860789&partnerID=8YFLogxK

M3 - Conference contribution

VL - 4

SP - 2361

EP - 2367

BT - Proceedings of the International Joint Conference on Neural Networks

ER -