Loading...
Please wait, while we are loading the content...
Similar Documents
Three global exponential convergence results of the gpnn for solving generalized linear variational inequalities.
| Content Provider | CiteSeerX |
|---|---|
| Author | Hu, Xiaolin Zeng, Zhigang Zhang, Bo |
| Abstract | Abstract. The general projection neural network (GPNN) is a versa-tile recurrent neural network model capable of solving a variety of opti-mization problems and variational inequalities. In a recent article [IEEE Trans. Neural Netw., 18(6), 1697-1708, 2007], the linear case of GPNN was studied extensively from the viewpoint of stability analysis, and it was utilized to solve the generalized linear variational inequality with various types of constraints. In the present paper we supplement three global exponential convergence results for the GPNN for solving these problems. The first one is different from those shown in the original arti-cle, and the other two are improved versions of two results in that article. The validity of the new results are demonstrated by numerical examples. 1 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Generalized Linear Variational Inequality Global Exponential Convergence Result Numerical Example Versa-tile Recurrent Neural Network Model Original Arti-cle Neural Netw General Projection Neural Network Linear Case Stability Analysis Various Type Recent Article Ieee Trans New Result Present Paper Opti-mization Problem Variational Inequality |
| Content Type | Text |
| Resource Type | Article |
