| 一种局部回归神经网络的快速算法 |
| |
| 引用本文： | 王飓,刘贺平.一种局部回归神经网络的快速算法[J].北京科技大学学报,2000,22(1):89-92. |
| |
| 作者姓名： | 王飓 刘贺平 |
| |
| 作者单位： | 北京科技大学信息工程学院,北京,100083 |
| |
| 摘 要： | 针对目前局部回归神经网络动态ＢＰ算法的误差导数计算复杂、收敛速度慢的缺陷，提出了一种新的快速算法、该算法是将信号流图引入动态ＢＰ算法，较好地解决了求导数的复杂性，同时采用ＢＦＧＳ算法另快了网络的收敛速度仿真结果表明了本算法的有效性。
|
| 关 键 词： | 神经网络 BP算法 BFGS 局部回归网络 快速算法 |
A Fast Algorithm for Recurrent Neural Networks |
| |
| WANG Ju,LIU Heping.A Fast Algorithm for Recurrent Neural Networks[J].Journal of University of Science and Technology Beijing,2000,22(1):89-92. |
| |
| Authors: | WANG Ju LIU Heping |
| |
| Institution: | WANG Ju,LIU Heping Information Engineering School,UST Beijing,Beijing 100083,China |
| |
| Abstract: | A new fast learning algorithm for recurrent neural networks is proposed. By introducing the signal flow graphs technique, it overcomes the disadvantage of complexity of the gradient of the error function. And for more fast convergence, the BFGS method is used. Simulation results show that the proposed algorithm converges faster than the traditional algorithm. |
| |
| Keywords: | recurrent neural networks dynamic BP algorithm signal flow graphs BFGS |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
