| 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.[点击复制] |
| HU Hong-jie,ER Lian-jie,LIU Jin-kun.Fast algorithm for diagonal recurrent neural networks control system[J].Control Theory and Technology,2002,19(5):777~780.[点击复制] |
|
| 一种快速对角回归神经网络控制算法 |
| Fast algorithm for diagonal recurrent neural networks control system |
| 摘要点击 1517 全文点击 793 投稿时间：2000-09-19 修订日期：2001-05-09 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 2002,19(5):777-780 |
| 中文关键词 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 |
| 英文关键词 DRNN adaptive learning rate weight vector and weight matrix convergence |
| 基金项目 |
|
| 中文摘要 |
| 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. |
| 英文摘要 |
| 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. |