| 一种可修正激励函数的BP算法 |
| |
| 引用本文： | 吕柏权,李天铎.一种可修正激励函数的BP算法[J].系统仿真学报,1997,9(4):15-18. |
| |
| 作者姓名： | 吕柏权 李天铎 |
| |
| 作者单位： | 清华大学热能系 |
| |
| 摘 要： | 以往的ＢＰ算法调节神经元网络的权值，其网络的隐层结点数、网络学习快慢程度及网络的泛化能力都与网络的激励函数有关的。为此，本文提出了一种带可以修正激励函数的ＢＰ算法，其特点是它能更好地模拟人脑神经元的特性。通过仿真验证此方法是非常有效的。
|
| 关 键 词： | 激励函数 BP算法 神经元网络 |
A BP Algorithm with Corrected Activation Function |
| |
| Lu Baiquan\ Li Tianduo\ Lu Chongde.A BP Algorithm with Corrected Activation Function[J].Journal of System Simulation,1997,9(4):15-18. |
| |
| Authors: | Lu Baiquan\ Li Tianduo\ Lu Chongde |
| |
| Institution: | Lu Baiquan\ Li Tianduo\ Lu Chongde Department of Thermal Engineering,Tsinghua University,Beijing 100084 |
| |
| Abstract: | BP algorithm is often used to correct weights of neural network because number of hidden nodes,studying speed and generation ability of neural network are related to activation function.This paper presents a BP algorithm with corrected activation function.Its advantage is that it can better simulate neuron of human being.Practical example indicates that the method works well. |
| |
| Keywords: | Activation function\ Back propagation algorithm\ Neural network |
| 本文献已被 CNKI 维普 等数据库收录！ |
