A functions localized neural network with branch gates

Qingyu Xiong, Kotaro Hirasawa, Takayuki Furuzuki, Junichi Murata

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In this paper, a functions localized network with branch gates (FLN-bg) is studied, which consists of a basic network and a branch gate network. The branch gate network is used to determine which intermediate nodes of the basic network should be connected to the output node with a gate coefficient ranging from 0 to 1. This determination will adjust the outputs of the intermediate nodes of the basic network depending on the values of the inputs of the network in order to realize a functions localized network. FLN-bg is applied to function approximation problems and a two-spiral problem. The simulation results show that FLN-bg exhibits better performance than conventional neural networks with comparable complexity.

Original languageEnglish
Pages (from-to)1461-1481
Number of pages21
JournalNeural Networks
Volume16
Issue number10
DOIs
Publication statusPublished - 2003 Dec

Fingerprint

Neural networks

Keywords

  • Branch gate
  • Functions localization
  • Fuzzy networks
  • Neural networks
  • Universal learning networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this

A functions localized neural network with branch gates. / Xiong, Qingyu; Hirasawa, Kotaro; Furuzuki, Takayuki; Murata, Junichi.

In: Neural Networks, Vol. 16, No. 10, 12.2003, p. 1461-1481.

Research output: Contribution to journalArticle

Xiong, Qingyu ; Hirasawa, Kotaro ; Furuzuki, Takayuki ; Murata, Junichi. / A functions localized neural network with branch gates. In: Neural Networks. 2003 ; Vol. 16, No. 10. pp. 1461-1481.
@article{462ee6cf5c334accb3f8971e72456ea4,
title = "A functions localized neural network with branch gates",
abstract = "In this paper, a functions localized network with branch gates (FLN-bg) is studied, which consists of a basic network and a branch gate network. The branch gate network is used to determine which intermediate nodes of the basic network should be connected to the output node with a gate coefficient ranging from 0 to 1. This determination will adjust the outputs of the intermediate nodes of the basic network depending on the values of the inputs of the network in order to realize a functions localized network. FLN-bg is applied to function approximation problems and a two-spiral problem. The simulation results show that FLN-bg exhibits better performance than conventional neural networks with comparable complexity.",
keywords = "Branch gate, Functions localization, Fuzzy networks, Neural networks, Universal learning networks",
author = "Qingyu Xiong and Kotaro Hirasawa and Takayuki Furuzuki and Junichi Murata",
year = "2003",
month = "12",
doi = "10.1016/S0893-6080(03)00211-9",
language = "English",
volume = "16",
pages = "1461--1481",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "10",

}

TY - JOUR

T1 - A functions localized neural network with branch gates

AU - Xiong, Qingyu

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

AU - Murata, Junichi

PY - 2003/12

Y1 - 2003/12

N2 - In this paper, a functions localized network with branch gates (FLN-bg) is studied, which consists of a basic network and a branch gate network. The branch gate network is used to determine which intermediate nodes of the basic network should be connected to the output node with a gate coefficient ranging from 0 to 1. This determination will adjust the outputs of the intermediate nodes of the basic network depending on the values of the inputs of the network in order to realize a functions localized network. FLN-bg is applied to function approximation problems and a two-spiral problem. The simulation results show that FLN-bg exhibits better performance than conventional neural networks with comparable complexity.

AB - In this paper, a functions localized network with branch gates (FLN-bg) is studied, which consists of a basic network and a branch gate network. The branch gate network is used to determine which intermediate nodes of the basic network should be connected to the output node with a gate coefficient ranging from 0 to 1. This determination will adjust the outputs of the intermediate nodes of the basic network depending on the values of the inputs of the network in order to realize a functions localized network. FLN-bg is applied to function approximation problems and a two-spiral problem. The simulation results show that FLN-bg exhibits better performance than conventional neural networks with comparable complexity.

KW - Branch gate

KW - Functions localization

KW - Fuzzy networks

KW - Neural networks

KW - Universal learning networks

UR - http://www.scopus.com/inward/record.url?scp=0242578092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242578092&partnerID=8YFLogxK

U2 - 10.1016/S0893-6080(03)00211-9

DO - 10.1016/S0893-6080(03)00211-9

M3 - Article

VL - 16

SP - 1461

EP - 1481

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 10

ER -