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
A new algorithm for improving the generalization performance and real-time ability of feedforward neural networks
Author(s): 
Pages: 241-244,264
Year: Issue:  3
Journal: ELECTRIC MACHINES AND CONTROL

Keyword:  前向神经网络泛化性能实时性能正则化方法;
Abstract: 提出一种基于正则化最小二乘的前向神经网络快速学习的混合算法.该算法将正则化方法和基于单个权值的局部化快速算法的优势结合起来,并加入隐节点删除算法,极大地提高了前向网络的泛化性能和实时性能,学习收敛速度快,精度较高.仿真结果表明了该混合算法的有效性.
Related Articles
No related articles found