Comparative study between functions distributed network and ordinary neural network

Qingyu Xiong, Kotaro Hirasawa, Takayuki Furuzuki, Junichi Murata

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

1 Citation (Scopus)

Abstract

In this paper, a functions distributed network, named Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR), is proposed. The point of the paper is to adjust the outputs of the intermediate nodes of the basic network using an additional branch control network. The adjustment means to multiply the nodes outputs by the coefficients ranging from zero to one, which is obtained from the branch control network. Therefore, the following are characterized in ULNs with BR, (1) the branch is cut when the coefficient of its branch is zero, and (2) multiplication is carried out in the nodes outputs adjustment when the coefficient takes a nonzero value. ULNs with BR is applied to two-spirals problem. The simulation results show that ULNs with BR exhibits better performance than the conventional neural networks with comparable complexity.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Pages1548-1553
Number of pages6
Volume3
Publication statusPublished - 2001
Externally publishedYes
Event2001 IEEE International Conference on Systems, Man and Cybernetics - Tucson, AZ, United States
Duration: 2001 Oct 72001 Oct 10

Other

Other2001 IEEE International Conference on Systems, Man and Cybernetics
CountryUnited States
CityTucson, AZ
Period01/10/701/10/10

Fingerprint

Neural networks

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Xiong, Q., Hirasawa, K., Furuzuki, T., & Murata, J. (2001). Comparative study between functions distributed network and ordinary neural network. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 3, pp. 1548-1553)

Comparative study between functions distributed network and ordinary neural network. / Xiong, Qingyu; Hirasawa, Kotaro; Furuzuki, Takayuki; Murata, Junichi.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 3 2001. p. 1548-1553.

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

Xiong, Q, Hirasawa, K, Furuzuki, T & Murata, J 2001, Comparative study between functions distributed network and ordinary neural network. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 3, pp. 1548-1553, 2001 IEEE International Conference on Systems, Man and Cybernetics, Tucson, AZ, United States, 01/10/7.
Xiong Q, Hirasawa K, Furuzuki T, Murata J. Comparative study between functions distributed network and ordinary neural network. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 3. 2001. p. 1548-1553
Xiong, Qingyu ; Hirasawa, Kotaro ; Furuzuki, Takayuki ; Murata, Junichi. / Comparative study between functions distributed network and ordinary neural network. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 3 2001. pp. 1548-1553
@inproceedings{de5d4e8e027f4614a64ede51a2e46034,
title = "Comparative study between functions distributed network and ordinary neural network",
abstract = "In this paper, a functions distributed network, named Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR), is proposed. The point of the paper is to adjust the outputs of the intermediate nodes of the basic network using an additional branch control network. The adjustment means to multiply the nodes outputs by the coefficients ranging from zero to one, which is obtained from the branch control network. Therefore, the following are characterized in ULNs with BR, (1) the branch is cut when the coefficient of its branch is zero, and (2) multiplication is carried out in the nodes outputs adjustment when the coefficient takes a nonzero value. ULNs with BR is applied to two-spirals problem. The simulation results show that ULNs with BR exhibits better performance than the conventional neural networks with comparable complexity.",
author = "Qingyu Xiong and Kotaro Hirasawa and Takayuki Furuzuki and Junichi Murata",
year = "2001",
language = "English",
volume = "3",
pages = "1548--1553",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

}

TY - GEN

T1 - Comparative study between functions distributed network and ordinary neural network

AU - Xiong, Qingyu

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

AU - Murata, Junichi

PY - 2001

Y1 - 2001

N2 - In this paper, a functions distributed network, named Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR), is proposed. The point of the paper is to adjust the outputs of the intermediate nodes of the basic network using an additional branch control network. The adjustment means to multiply the nodes outputs by the coefficients ranging from zero to one, which is obtained from the branch control network. Therefore, the following are characterized in ULNs with BR, (1) the branch is cut when the coefficient of its branch is zero, and (2) multiplication is carried out in the nodes outputs adjustment when the coefficient takes a nonzero value. ULNs with BR is applied to two-spirals problem. The simulation results show that ULNs with BR exhibits better performance than the conventional neural networks with comparable complexity.

AB - In this paper, a functions distributed network, named Universal Learning Networks with Branch Control of Relative Strength (ULNs with BR), is proposed. The point of the paper is to adjust the outputs of the intermediate nodes of the basic network using an additional branch control network. The adjustment means to multiply the nodes outputs by the coefficients ranging from zero to one, which is obtained from the branch control network. Therefore, the following are characterized in ULNs with BR, (1) the branch is cut when the coefficient of its branch is zero, and (2) multiplication is carried out in the nodes outputs adjustment when the coefficient takes a nonzero value. ULNs with BR is applied to two-spirals problem. The simulation results show that ULNs with BR exhibits better performance than the conventional neural networks with comparable complexity.

UR - http://www.scopus.com/inward/record.url?scp=0035723112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035723112&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 1548

EP - 1553

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

ER -