One-Layer Continuous- and Discrete-Time Projection Neural Networks for Solving Variational Inequalities and Related Optimization Problems Academic Article

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. 2013 IEEE.

authors

• Huang, Tingwen

published proceedings

• IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

author list (cited authors)

• Liu, Q., Huang, T., & Wang, J.

citation count

• 52

complete list of authors

• Liu, Qingshan||Huang, Tingwen||Wang, Jun

publication date

• July 2014

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• n2162-237XISSN  Journal

keywords

• Constrained Optimization
• Global Convergence
• Lyapunov Stability
• Projection Neural Network
• Variational Inequalities

Digital Object Identifier (DOI)

• 10.1109/TNNLS.2013.2292893

start page

• 1308

end page

• 1318

volume

• 25

issue

• 7

URL

• http://dx.doi.org/10.1109/tnnls.2013.2292893