Application of likelihood search method to neural networks learning

Masaru Koga; Kotaro Hirasawa; Junichi Murata; Masanao Ohbayashi

Application of likelihood search method to neural networks learning

Masaru Koga, Kotaro Hirasawa, Junichi Murata, Masanao Ohbayashi

Section of Measurement and Control Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

This article mainly compares learning performances between the Likelihood Search Method (L.S.M.) and the Back Propagation Method (B.P.). The performances are evaluated by the simulations which include both static and dynamic Neural Networks (N.N.) learning problems. In the simulations, N.N. is trained to realize nonlinear functions or control a nonlinear crane system by using the L.S.M. and B.P.. Simulation results show that the L.S.M. is superior to the B.P. because of the ability of intensification and diversification of the search.

Original language	English
Pages (from-to)	83-97
Number of pages	15
Journal	Memoirs of the Kyushu University, Faculty of Engineering
Volume	56
Issue number	2
Publication status	Published - Jun 1 1996

All Science Journal Classification (ASJC) codes

Energy(all)
Atmospheric Science
Earth and Planetary Sciences(all)
Management of Technology and Innovation

Fingerprint Dive into the research topics of 'Application of likelihood search method to neural networks learning'. Together they form a unique fingerprint.

Cite this

@article{65d89ee57d6a416d92ea41ec54cade0d,

title = "Application of likelihood search method to neural networks learning",

abstract = "This article mainly compares learning performances between the Likelihood Search Method (L.S.M.) and the Back Propagation Method (B.P.). The performances are evaluated by the simulations which include both static and dynamic Neural Networks (N.N.) learning problems. In the simulations, N.N. is trained to realize nonlinear functions or control a nonlinear crane system by using the L.S.M. and B.P.. Simulation results show that the L.S.M. is superior to the B.P. because of the ability of intensification and diversification of the search.",

author = "Masaru Koga and Kotaro Hirasawa and Junichi Murata and Masanao Ohbayashi",

year = "1996",

month = jun,

day = "1",

language = "English",

volume = "56",

pages = "83--97",

journal = "Memoirs of the Faculty of Engineering, Kyushu University",

issn = "1345-868X",

publisher = "Kyushu University, Faculty of Science",

number = "2",

}

TY - JOUR

T1 - Application of likelihood search method to neural networks learning

AU - Koga, Masaru

AU - Hirasawa, Kotaro

AU - Murata, Junichi

AU - Ohbayashi, Masanao

PY - 1996/6/1

Y1 - 1996/6/1

N2 - This article mainly compares learning performances between the Likelihood Search Method (L.S.M.) and the Back Propagation Method (B.P.). The performances are evaluated by the simulations which include both static and dynamic Neural Networks (N.N.) learning problems. In the simulations, N.N. is trained to realize nonlinear functions or control a nonlinear crane system by using the L.S.M. and B.P.. Simulation results show that the L.S.M. is superior to the B.P. because of the ability of intensification and diversification of the search.

AB - This article mainly compares learning performances between the Likelihood Search Method (L.S.M.) and the Back Propagation Method (B.P.). The performances are evaluated by the simulations which include both static and dynamic Neural Networks (N.N.) learning problems. In the simulations, N.N. is trained to realize nonlinear functions or control a nonlinear crane system by using the L.S.M. and B.P.. Simulation results show that the L.S.M. is superior to the B.P. because of the ability of intensification and diversification of the search.

UR - http://www.scopus.com/inward/record.url?scp=0030174066&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030174066&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030174066

VL - 56

SP - 83

EP - 97

JO - Memoirs of the Faculty of Engineering, Kyushu University

JF - Memoirs of the Faculty of Engineering, Kyushu University

SN - 1345-868X

IS - 2

ER -

Application of likelihood search method to neural networks learning

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Cite this