CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 先进机器人
A recurrent neural network for non-smooth nonlinear programming problems
Long Cheng; Zeng-Guang Hou; Min Tan; Xiuqing Wang; Zengshun Zhao; Sanqing Hu
2007
Conference Name IEEE International Joint Conference on Neural Networks (IJCNN)
Conference DateAUG 12-17, 2007
Conference PlaceOrlando
CountryUSA
AbstractA recurrent neural network is proposed for solving non-smooth nonlinear programming problems, which can be regarded as a generalization of the smooth nonlinear programming neural network used in [1]. Based on the non-smooth analysis and the theory of differential inclusions, the proposed neural network is demonstrated to be globally convergent to the exact optimal solution of the original optimization problem. Compared with the existing neural networks, the proposed approach takes both equality and inequality constraints into account, and no penalty parameters have to be estimated beforehand. Therefore, it can solve a larger class of non-smooth programming problems. Finally, several illustrative examples are given to show the effectiveness of the proposed neural network.
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23162
Collection复杂系统管理与控制国家重点实验室_先进机器人
Recommended Citation
GB/T 7714
Long Cheng,Zeng-Guang Hou,Min Tan,et al. A recurrent neural network for non-smooth nonlinear programming problems[C],2007.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Long Cheng]'s Articles
[Zeng-Guang Hou]'s Articles
[Min Tan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Long Cheng]'s Articles
[Zeng-Guang Hou]'s Articles
[Min Tan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Long Cheng]'s Articles
[Zeng-Guang Hou]'s Articles
[Min Tan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.