期刊
NEUROCOMPUTING
卷 286, 期 -, 页码 11-18出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2018.01.046
关键词
Elman neural network; Learning rate; Convergence proof
资金
- Natural Science Foundation of China [61673187, 61673188]
- Research Project of Hubei Provincial Department of Education of China [Q20161406]
- NPRP from Qatar National Research Fund [NPRP 8-274-2-107]
Elman neural network (ENN) is one of recurrent neural networks (RNNs). Comparing to traditional neural networks, ENN has additional inputs from the hidden layer, which forms a new layer-the context layer. So the standard back-propagation (BP) algorithm used in ENN is called Elman back-propagation algorithm (EBP). ENN can be applied to solve prediction problems of discrete time sequence. However, the EBP algorithm suffers from low convergence speed and poor generalization performance. To solve this problem, a new learning rate scheme is proposed, the convergence of new proposed scheme is proved. Furthermore, the contrast experiment is utilized to demonstrate the effectiveness of the proposed scheme from the aspects of convergence speed and consumption time with some popular schemes such as the original ENN, and PSO-ENN which uses PSO algorithm to search the best structure of ENN. The experience shows that the modified method proposed in this paper works best. (C) 2018 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据