摘要
文章对神经网络进行了分析,探讨了神经网络中存在的主要问题和若干改进方案及其优劣和特点,给出了利用改进型BP神经网络进行训练时动量项系数、学习率和隐层单元数的优化方法,在实际应用中有了一定的概念支持。
Studies of neural networks and discussing the main problems existed in the neural networks, the improvement measures, the advantage and disadvantage and the features were inquired in the paper. The momentum coefficient, learn rate and the number of hidden units were provided utilizing the BP （Back Propagation） neural networks. The methods are useful about the notion in the practice.
出处
《微计算机信息》
2009年第1期179-180,共2页
Control & Automation
关键词
神经网络
BP算法
智能诊断
故障诊断
Neural Network
BP（Back Propagation）
Intelligent Diagnosis
Fault Diagnosis
