| 一种改进型神经网络算法NN-LMBP |
| |
| 引用本文： | 鞠儒生,王学宁,刘宝宏,黄柯棣. 一种改进型神经网络算法NN-LMBP[J]. 系统仿真学报, 2007, 19(21): 4857-4859,4863 |
| |
| 作者姓名： | 鞠儒生 王学宁 刘宝宏 黄柯棣 |
| |
| 作者单位： | 国防科技大学,机电工程与自动化学院,长沙,410073 |
| |
| 摘 要： | 提出最近邻Levenberg—Marquardt误差反向传播神经网络算法。针对BP神经网络收敛速度慢的不足，利用Levenberg—Marquardt优化算法进行改进。同时为了提高神经网络的泛化能力，进一步基于最近邻算法对样本进行修剪。试验表明，与一般神经网络算法相比，NN-LMBP在改善神经网络泛化能力的基础上，有效地提高了神经网络收敛的速度。
|
| 关 键 词： | 神经网络 Levenberg-Marquardt算法 最近邻 修剪 |
| 文章编号： | 1004-731X（2007）21-4857-03 |
| 收稿时间： | 2006-08-31 |
| 修稿时间： | 2006-08-312007-04-03 |
Improved Neural Network Algorithm NN-LMBP |
| |
| JU Ru-sheng,WANG Xue-ning,LIU Bao-hong,HUANG Ke-di. Improved Neural Network Algorithm NN-LMBP[J]. Journal of System Simulation, 2007, 19(21): 4857-4859,4863 |
| |
| Authors: | JU Ru-sheng WANG Xue-ning LIU Bao-hong HUANG Ke-di |
| |
| Affiliation: | 1.School of Electromechanical Engineering and Automation, National University of Defense Technology, Changsha 410073, China; 2.Beijing Qinghe Building Zi 9, Beijing 100085, China |
| |
| Abstract: | An algorithm of Nearest Neighbor Levenberg-Marquardt Back Propagation Neural Networks(NN-LMBP) was put forward.The optimization algorithm Levenberg-Marquardt was utilized to increase the convergence speed of BP Neural Networks.Besides,based on algorithm of Nearest Neighbor,a strategy of sample pruning was adopted to improve the generation performance of Neural Networks.Experiments show that compared with normal Neural Networks,NN-LMBP is better in speed and generalization ability. |
| |
| Keywords: | Neural Networks Levenberg-Marquardt algorithm Nearest Neighbor Prune |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
