| 神经网络的具有自适应动量和步长的伪牛顿算法 |
| |
| 引用本文： | 李歧强,顾永如,钱积新.神经网络的具有自适应动量和步长的伪牛顿算法[J].信息与控制,1998,27(2):146-151. |
| |
| 作者姓名： | 李歧强 顾永如 钱积新 |
| |
| 作者单位： | 浙江大学工业控制技术国家重点实验室,浙江大学工业控制技术研究所,杭州,310027 |
| |
| 摘 要： | 以单隐层的３层前向神经网络为基础，由自适应ＢＰ算法和牛顿优化算法导出了自适应步长和动量解耦的伪牛顿算法（ＱＮＡＤＳＭ）．该算法计算量小，收敛速度快．文中还给出了该算法的收敛性证明、算法的仿真结果及其它算法的比较结果，并对网络的训练及该算法的特点作了进一步的讨论．仿真结果表明ＱＮＡＤＳＭ算法是一种有效的工程实用算法．
|
| 关 键 词： | 神经网络 自适应动量 步长 伪牛顿法 系统辨识 |
QUASI NEWTON ALGORITHM OF ADAPTIVE DECOUPLED STEP AND MOMENTUM FOR NEURAL NETWORK |
| |
| Li Qiqiang,GU YONGRU,QIAN Jixin.QUASI NEWTON ALGORITHM OF ADAPTIVE DECOUPLED STEP AND MOMENTUM FOR NEURAL NETWORK[J].Information and Control,1998,27(2):146-151. |
| |
| Authors: | Li Qiqiang GU YONGRU QIAN Jixin |
| |
| Abstract: | In this paper, a quasi Newton algorithm with adaptive decoupled step and momentum(QNADSM) used in three layered feedforward neural network is derived from adaptive BP algorithm and Newton algorithm, which is of less computational amount and fast convergence. In this note we also present the proof of the convergence and simulation results. The simulation results demonstrate that QNADSM algorithm is an effectively practical algorithm. |
| |
| Keywords: | Feedforward neural networks Adaptive Decouple BP algorithm Newton algorithm Quasi Newton algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
