摘要
利用改进的 Elman神经网络对 3个典型的混沌时间序列在不同的噪声水平下进行预测 ,探讨了神经网络学习与泛化之间的关系 ,通过试凑法给出了 Elman最优的隐节点个数。并利用3种指标对预测结果进行了评估 ,结果显示
This paper uses the improved Elman neural networks to predict three typical chaos time series under different noise conditions. It also discusses the relationship between learning and generalization of the neural networks and gives the optimal number of Elman's hidden layer units. In addition, the prediction results are evaluated by three targets which show the perfect performance of Elman networks in the prediction of the chaos time series.
出处
《华东理工大学学报（社会科学版）》
CAS
2002年第S1期30-33,共4页
Journal of East China University of Science and Technology：Social Science Edition
