��ҳ��

��Ƶ��ѱ��վ��Ա��أ�

��ԭ��Ը�ҳ��ķ��ʹ��Ƶ��

��ν��

1��ύ��ݣ�

2��վ�йܣ��ϵ�ռ��ṩ�̣�

3��ͨ��վ�ÿͣ��ϵ��վ��Ա

��վ��Ա��¼��ȫ��

Related citation:

PengYong,ZHOU Hui-cheng.Fuzzy optimization neural network model based on LM algorithm[J].Journal of Harbin Institute Of Technology(New Series),2010,17(3):431-436.DOI:10.11916/j.issn.1005-9113.2010.03.027.

【Print】【HTML】【PDF download】【View/Add Comment】【Download reader】【 Close 】

←Previous|Next→

Back Issue Advanced Search

This paper has been: browsed 1170times downloaded 569times	码上扫一扫！
Shared by: Wechat More Font:larger+\|default\|smaller-
Fuzzy optimization neural network model based on LM algorithm

Author Name	Affiliation
PengYong	School of Civil and Hydraulic Engineering,Dalian University of Technology,Dalian 116023,China
ZHOU Hui-cheng	School of Civil and Hydraulic Engineering,Dalian University of Technology,Dalian 116023,China

Abstract:

A new fuzzy optimization neural network model is proposed based on the Levenberg-Marquardt (LM) algorithm on account of the disadvantages of slow convergence of traditional fuzzy optimization neural network model. In this new model,the gradient descent algorithm is replaced by the LM algorithm to obtain the minimum of output errors during network training,which changes the weights adjusting equations of the network and increases the training speed. Moreover,to avoid the results yielding to local minimum,the transfer function is also revised to sigmoid function. A case study is utilized to validate this new model,and the results reveal that the new model fast training speed and better forecasting capability.

Key words: fuzzy optimization neural network Levenberg-Marquardt algorithm transfer function

DOI：10.11916/j.issn.1005-9113.2010.03.027

Clc Number:TP183

Fund: