Neural networks with node gates

H. M. Myint, Junichi Murata, T. Nakazono, K. Hirasawa

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Function approximation problems for the ordinary neural networks may be rather difficult, if the function becomes complicated, due to the necessity of big network size and the possibilities of many local minima. A promissing way to solve these difficulties is the localization of the problem. According to this concept, a new architecture of neural network is proposed namely neural network with node gates. In this paper, a function approximation example is provided to demonstrate the better performance of the proposed network than the ordinary neural network.

Original languageEnglish
Pages253-257
Number of pages5
Publication statusPublished - Dec 1 2000
Event9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000 - Osaka, Japan
Duration: Sep 27 2000Sep 29 2000

Other

Other9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000
CountryJapan
CityOsaka
Period9/27/009/29/00

Fingerprint

Neural networks

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Software

Cite this

Myint, H. M., Murata, J., Nakazono, T., & Hirasawa, K. (2000). Neural networks with node gates. 253-257. Paper presented at 9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000, Osaka, Japan.

Neural networks with node gates. / Myint, H. M.; Murata, Junichi; Nakazono, T.; Hirasawa, K.

2000. 253-257 Paper presented at 9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000, Osaka, Japan.

Research output: Contribution to conferencePaper

Myint, HM, Murata, J, Nakazono, T & Hirasawa, K 2000, 'Neural networks with node gates', Paper presented at 9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000, Osaka, Japan, 9/27/00 - 9/29/00 pp. 253-257.
Myint HM, Murata J, Nakazono T, Hirasawa K. Neural networks with node gates. 2000. Paper presented at 9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000, Osaka, Japan.
Myint, H. M. ; Murata, Junichi ; Nakazono, T. ; Hirasawa, K. / Neural networks with node gates. Paper presented at 9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000, Osaka, Japan.5 p.
@conference{fd13cbb4595248cdb1472022c850c641,
title = "Neural networks with node gates",
abstract = "Function approximation problems for the ordinary neural networks may be rather difficult, if the function becomes complicated, due to the necessity of big network size and the possibilities of many local minima. A promissing way to solve these difficulties is the localization of the problem. According to this concept, a new architecture of neural network is proposed namely neural network with node gates. In this paper, a function approximation example is provided to demonstrate the better performance of the proposed network than the ordinary neural network.",
author = "Myint, {H. M.} and Junichi Murata and T. Nakazono and K. Hirasawa",
year = "2000",
month = "12",
day = "1",
language = "English",
pages = "253--257",
note = "9th IEEE International Workshop on Robot and Human Interactive Communication RO-MAN2000 ; Conference date: 27-09-2000 Through 29-09-2000",

}

TY - CONF

T1 - Neural networks with node gates

AU - Myint, H. M.

AU - Murata, Junichi

AU - Nakazono, T.

AU - Hirasawa, K.

PY - 2000/12/1

Y1 - 2000/12/1

N2 - Function approximation problems for the ordinary neural networks may be rather difficult, if the function becomes complicated, due to the necessity of big network size and the possibilities of many local minima. A promissing way to solve these difficulties is the localization of the problem. According to this concept, a new architecture of neural network is proposed namely neural network with node gates. In this paper, a function approximation example is provided to demonstrate the better performance of the proposed network than the ordinary neural network.

AB - Function approximation problems for the ordinary neural networks may be rather difficult, if the function becomes complicated, due to the necessity of big network size and the possibilities of many local minima. A promissing way to solve these difficulties is the localization of the problem. According to this concept, a new architecture of neural network is proposed namely neural network with node gates. In this paper, a function approximation example is provided to demonstrate the better performance of the proposed network than the ordinary neural network.

UR - http://www.scopus.com/inward/record.url?scp=0034586821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034586821&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0034586821

SP - 253

EP - 257

ER -