标题:An efficient conjugate gradient based learning algorithm for multiple optimal learning factors of multilayer perceptron neural network
作者:Cai, Xun ;Tyagi, Kanishka ;Manry, Michael T. ;Chen, Zhi
通讯作者:Cai, Xun
作者机构:[Cai, Xun ;Chen, Zhi ] School of Computer Science and Technology, Shandong University, Jinan; 25010, China;[Tyagi, Kanishka ;Manry, Michael T. ] Depar 更多
会议名称:2014 International Joint Conference on Neural Networks, IJCNN 2014
会议日期:6 July 2014 through 11 July 2014
来源:Proceedings of the International Joint Conference on Neural Networks
出版年:2014
页码:1093-1099
DOI:10.1109/IJCNN.2014.6889907
关键词:conjugate gradient method; Multilayer Perceptron Neural Network; multiple learning factors
摘要:In this paper, a second order learning algorithm based on Conjugate Gradient (CG) method for finding Multiple Optimal Learning Factors (MOLFs) of multilayer perceptron neural network is proposed in details. The experimental results on several benchmarks show that, compared with One Optimal Learning Factor algorithm with Optimal Output Weights (lOLF-OWO) and Levenberg-Marquardt learning algorithm (LM), our proposed CG based MOLF method with optimal output weights which is also called MOLFCG-OWO algorithm has not only significantly faster convergence rate than that of lOLF and even super to that of LM learning algorithm for some datasets with much less computational time, but also more generalization capability than lOLF-OWO. Thus, MOLFCG-OWO algorithm is suggested better choice for some practical applications. © 2014 IEEE.
收录类别:EI;SCOPUS
Scopus被引频次:1
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84908494295&doi=10.1109%2fIJCNN.2014.6889907&partnerID=40&md5=ddfca9ada2d07350a0fba1146d4e01b8
TOP