摘要
对BP神经网络的结构及其训练算法进行了研究,并针对传统BP算法的缺陷,提出了一种采用L-M算法的改进 BP神经网络。在此基础上建立了基于改进BP神经网络的非线性系统预测模型,并通过具体的仿真及实践结果验证了改进BP 神经网络的有效性。
The structure of BP neural networks and its training algorithm are studied. Aiming at the shortage of the conventional BP algorithm, the BP neural networks improved by L-M algorithm is put forward . On the basis of these, the predictive model of the nonlinear system is set up based on improved BP neural networks .By means of the simulation and practice, the effectiveness of the improved BP neural networks has been further testified.
出处
《计算机测量与控制》
CSCD
2005年第1期39-42,共4页
Computer Measurement &Control