The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
Study and Application of a Class of Neural Networks Model with Better Generalization Ability
Author(s): 
Pages: 6-11,17
Year: Issue:  2
Journal: AEROSPACE CONTROL

Keyword:  神经网络建模泛化能力氧化铝浓度;
Abstract: 分析了影响神经网络模型泛化能力的因素.以电解铝过程中氧化铝浓度的神经网络软测量为例,提出了利用先验知识确定网络结构,采用特定实验保证样本数量和质量,离线训练加在线学习修正模型等措施,改善神经网络模型的泛化能力.现场应用表明这些措施是有效的.这样建立的神经网络模型准确,泛化能力强,为实现过程的先进控制提供了可靠保障.
Related Articles
No related articles found