摘要
为提高神经网络的预测精度,对现有的误差反传网络训练算法进行了改进。对三层误差反传网络进行了结构扩展,在训练过的三层网络中,动态增加一个具有线性激活函数的辅助隐层,形成一种新的网络扩展模型。用改进的蚁群算法对新增权值参数进行训练,着重阐述算法的实现过程及算法分析。最后,设计了一组催化剂活性预测实验,对算法改进前后的预测能力及训练误差进行了对比。结果表明,采用该模型及训练算法,可以在不影响网络表达能力的基础上提高网络的训练精度及预测精度,改善了网络的泛化能力。
To enhance the forecast precision of the neural network, an improved BackPropagation （BP） training algorithm was proposed. The existing three-layer structure of BP neural network was extended. An assistant hidden layer was dynamically increased in the trained-three-layer BP neural network to form a new neural network expansion model. The newly added weights and thresholds of BP neural network were trained by an improved ant colony algorithm. The implementation processes and analysis olr the algorithm were elaborated in depth. An experiment was designed to compare the forecast preci- sion and the training error of the BP network to predict the catalyst activity by its original algorithm and the improved train- ing algorithm. Results showed that the hiddewLayer extension model and the improved training algorithm could improve the training precision and the forecast precision without affecting the expression of the neural network. On the other hand, it was also able to enhance the generalization ability of the network.
出处
《计算机集成制造系统》
EI
CSCD
北大核心
2008年第11期2284-2288,共5页
Computer Integrated Manufacturing Systems
基金
国家863计划资助项目(2006AA06Z224)~~
关键词
误差反传
神经网络
扩展隐层
训练算法
预测精度
baekpropagation
neural networks
extending hidden layer
training algorithm
forecast precision
