One-Layer Continuous-and Discrete-Time Projection Neural Networks for Solving Variational Inequalities and Related Optimization Problems
- 11 December 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 25 (7) , 1308-1318
Abstract
This paper presents one-layer projection neural networks based on projection operators for solving constrained variational inequalities and related optimization problems. Sufficient conditions for global convergence of the proposed neural networks are provided based on Lyapunov stability. Compared with the existing neural networks for variational inequalities and optimization, the proposed neural networks have lower model complexities. In addition, some improved criteria for global convergence are given. Compared with our previous work, a design parameter has been added in the projection neural network models, and it results in some improved performance. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural networks.Keywords
Funding Information
- National Natural Science Foundation of China (61105060)
- Program for New Century Excellent Talents in University (NCET-12-0114)
- Natural Science Foundation of Jiangsu Province of China (BK2011594)
- Fundamental Research Funds for the Central Universities
- Qatar National Research Fund (NPRP-4-1162-1-181)
- Research Grants Council of the Hong Kong Special Administrative Region (CUHK416811E, CUHK416812E)
- National Natural Science Foundation of China (61273307)
This publication has 36 references indexed in Scilit:
- A One-Layer Projection Neural Network for Nonsmooth Optimization Subject to Linear Equalities and Bound ConstraintsIEEE Transactions on Neural Networks and Learning Systems, 2013
- Design of second order neural networks as dynamical control systems that aim to minimize nonconvex scalar functionsNeurocomputing, 2012
- Global exponential stability of discrete-time recurrent neural network for solving quadratic programming problems subject to linear constraintsNeurocomputing, 2011
- Perceptron training algorithms designed using discrete-time control Liapunov functionsNeurocomputing, 2009
- A Recurrent Neural Network for Solving Nonlinear Convex Programs Subject to Linear ConstraintsIEEE Transactions on Neural Networks, 2005
- Global exponential stability of discrete-time neural networks for constrained quadratic optimizationNeurocomputing, 2004
- Convergence analysis of a discrete-time recurrent neural network to perform quadratic real optimization with bound constraintsIEEE Transactions on Neural Networks, 1998
- Linear Matrix Inequalities in System and Control Theory1994
- Neural network for quadratic optimization with bound constraintsIEEE Transactions on Neural Networks, 1993
- The Stability of Dynamical Systems1976