| 模糊回声状态网络 |
| |
| 引用本文： | 彭宇,王建民,彭喜元.模糊回声状态网络[J].电子学报,2011,39(7):1538-1544. |
| |
| 作者姓名： | 彭宇 王建民 彭喜元 |
| |
| 作者单位： | 1. 哈尔滨工业大学自动化测试与控制研究所,黑龙江哈尔滨,150080
2. 哈尔滨工业大学自动化测试与控制研究所,黑龙江哈尔滨150080;哈尔滨理工大学电子科学与技术系,黑龙江哈尔滨150001 |
| |
| 基金项目： | 装备预研重点基金(No.9140A17040409HT01); 教育部新世纪优秀人才支持计划基金(No.NCET-10-0062); 教育部高等学校博士学科点专项科研基金(No.20092302110013) |
| |
| 摘 要： | 针对基于梯度下降的模糊递归神经网络训练效率低、容易陷入局部极小的缺点,本文基于回声状态网络(Echo State Networks,ESNs)和TS模型提出一种新的模糊模型结构——模糊回声状态网络(Fuzzy Echo State Networks,FESNs).FESNs由多条TS类型的模糊规则组成,规则后件采用ES...
|
| 关 键 词： | 回声状态网络 储备池 TS模型 动态系统建模 |
| 收稿时间： | 2010-03-30 |
Fuzzy Echo State Networks |
| |
| PENG Yu,WANG Jian-min,PENG Xi-yuan.Fuzzy Echo State Networks[J].Acta Electronica Sinica,2011,39(7):1538-1544. |
| |
| Authors: | PENG Yu WANG Jian-min PENG Xi-yuan |
| |
| Affiliation: | PENG Yu1,WANG Jian-min1,2,PENG Xi-yuan1(1.Automatic Test and Control Institute,Harbin Institute of Technology,Harbin,Heilongjiang 150080,China,2.Department of Electronics Science & Technology,Harbin University of Science and Technology,Heilongjiang 150001,China) |
| |
| Abstract: | Recurrent fuzzy neural networks,which is usually trained by gradient descent,have some inherent shortcomings such as inefficiency of training process,local minimum.In this paper,we proposed a novel fuzzy neural network based on Echo state network and TS fuzzy model,called fuzzy echo state network(FESN),which is a generality of both TS modal and ESN.FESNs consist of several fuzzy IF-THEN rules,each of which has a ESN as consequent part.We illustrate that FESNs have some interesting characteristics,such as be... |
| |
| Keywords: | echo state networks reservoir TS model modeling dynamical system |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
|
