| 基于重置的拟牛顿动态前馈神经网络 |
| |
| 引用本文： | 刘宁.基于重置的拟牛顿动态前馈神经网络[J].辽宁工程技术大学学报(自然科学版),2004,23(4):560-563. |
| |
| 作者姓名： | 刘宁 |
| |
| 作者单位： | 南京财经大学,国际经贸学院,江苏南京,210003 |
| |
| 基金项目： | 国家自然科学基金资助项目(10271025) |
| |
| 摘 要： | 前馈神经网络的结构直接影响网络的性能。构造基于拟牛顿法(Quasi．NewtonAlgorithm)的前馈神经网络模型，为了优化神经网络结构，尝试引入重置算法(EarlyRestartAlgorithm)，得到基于重置的拟牛顿动态前馈神经网络。对比实验表明，重置算法的引入有效地解决了结构优化问题，优化后的神经网络具有良好的收敛性与稳定性。
|
| 关 键 词： | 重置算法 神经网络 结构优化 |
| 文章编号： | 1008-0562(2004)04-0560-04 |
| 修稿时间： | 2003年7月22日 |
Dynamic quasi-newton feed forward neural network based on early restart algorithm |
| |
| LIU Ning.Dynamic quasi-newton feed forward neural network based on early restart algorithm[J].Journal of Liaoning Technical University (Natural Science Edition),2004,23(4):560-563. |
| |
| Authors: | LIU Ning |
| |
| Abstract: | The structure of feed forward neural network will affect its performance directly. The feed forward neural network based on Quasi-Newton algorithm is proposed firstly. Then, in order to optimize the neural network structure, the early restart algorithm is introduced and applied to the Quasi-Newton feed forward neural network.. The comparative experiment results demonstrate that the early restart algorithm can solve the structure optimization problem of Neural Network effectively, and the revised neural network performs well in convergence and stability. |
| |
| Keywords: | early restart algorithm neural network structure optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
