| 一种快速对角回归神经网络控制算法 |
| |
| 引用本文： | 扈宏杰,尔联洁,刘金琨.一种快速对角回归神经网络控制算法[J].控制理论与应用,2002,19(5):777-780. |
| |
| 作者姓名： | 扈宏杰 尔联洁 刘金琨 |
| |
| 作者单位： | 北京航空航天大学,自动控制系,北京,100083 |
| |
| 摘 要： | 文1]定理1给出了一个基于Lyapunov函数的三层对角回归神经网络(DRNN)任意权参数学习速率的自适应调整算法, 而推导各层权自适应学习速率时没有严格满足定理1成立的必要条件, 故没能找到各学习速率的准确范围. 依据文1]定理1,精确给出了各权向量及权矩阵学习速率的调整算法, 结果表明DRNN应具有更大的学习速率, 对应更加快速的收敛算法. 给出了相应的仿真结果.
|
| 关 键 词： | 对角回归神经网络 自适应学习速率 权向量及权矩阵 收敛性 |
| 文章编号： | 1000-8152(2002)04-0777-04 |
| 收稿时间： | 2000/9/19 0:00:00 |
| 修稿时间： | 5/9/2001 12:00:00 AM |
Fast algorithm for diagonal recurrent neural networks control system |
| |
| HU Hong-jie,ER Lian-jie and LIU Jin-kun.Fast algorithm for diagonal recurrent neural networks control system[J].Control Theory & Applications,2002,19(5):777-780. |
| |
| Authors: | HU Hong-jie ER Lian-jie and LIU Jin-kun |
| |
| Affiliation: | Department of Control, Beijing University of Aeronautics & Astronautics, Beijing 100083,China;Department of Control, Beijing University of Aeronautics & Astronautics, Beijing 100083,China;Department of Control, Beijing University of Aeronautics & Astronautics, Beijing 100083,China |
| |
| Abstract: | Convergence Theorem 1 in Ref. was given for three layers diagonal recurrent neural networks (DRNN) by introducing a Lyapunov function. Because the essential condition to Theorem 1 was neglected upper limits of learning rates for every weight vectors and matrix were not attained. Much bigger learning rates of all weight vectors and matrix are deduced precisely on the basis of convergence theorem 1 in Ref. , so a fast iterative algorithm is obtained. Simulation results are included. |
| |
| Keywords: | DRNN adaptive learning rate weight vector and weight matrix convergence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《控制理论与应用》浏览原始摘要信息 |
|
点击此处可从《控制理论与应用》下载全文 |
|
