Visible to the public One-Layer Continuous-and Discrete-Time Projection Neural Networks for Solving Variational Inequalities and Related Optimization Problems

TitleOne-Layer Continuous-and Discrete-Time Projection Neural Networks for Solving Variational Inequalities and Related Optimization Problems
Publication TypeJournal Article
Year of Publication2014
AuthorsQingshan Liu, Tingwen Huang, Jun Wang
JournalNeural Networks and Learning Systems, IEEE Transactions on
Volume25
Pagination1308-1318
Date PublishedJuly
ISSN2162-237X
Keywordsconstrained optimization, constrained variational inequalities, convergence, discrete time systems, Educational institutions, global convergence, Lyapunov methods, Lyapunov stability, Mathematical model, neural nets, Neural networks, one-layer continuous-time projection neural networks, one-layer discrete-time projection neural networks, optimisation, Optimization, optimization problems, projection neural network, sufficient conditions, variational inequalities, variational inequalities., variational techniques, Vectors
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.

DOI10.1109/TNNLS.2013.2292893
Citation Key6680760