A project neural network for solving degenerate convex quadratic program

Authors:
Xiaoping Xue;Wei Bian
Affiliations:
Department of Mathematics, Harbin Institute of Technology, Harbin 150001, PR China;Department of Mathematics, Harbin Institute of Technology, Harbin 150001, PR China
Venue:
Neurocomputing
Year:
2007

Citing 8
Cited 8

Parallel and distributed computation: numerical methods

Parallel and distributed computation: numerical methods
A recurrent neural network for solving linear projection equations

Neural Networks
A simple and high performance neural network for quadratic programming problems

Applied Mathematics and Computation
A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations

Neural Networks
An improved neural network for convex quadratic optimization with application to real-time beamforming

Neurocomputing
A dual neural network for kinematic control of redundant robotmanipulators

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new neural network for solving linear and quadratic programming problems

IEEE Transactions on Neural Networks
Neural network for quadratic optimization with bound constraints

IEEE Transactions on Neural Networks

A project neural network for solving degenerate quadratic minimax problem with linear constraints

Neurocomputing
Global Exponential Stability and Global Convergence in Finite Time of Neural Networks with Discontinuous Activations

Neural Processing Letters
A new recurrent neural network for solving convex quadratic programming problems with an application to the k-winners-take-all problem

IEEE Transactions on Neural Networks
A dynamical model for solving degenerate quadratic minimax problems with constraints

Journal of Computational and Applied Mathematics
A capable neural network model for solving the maximum flow problem

Journal of Computational and Applied Mathematics
Solving general convex nonlinear optimization problems by an efficient neurodynamic model

Engineering Applications of Artificial Intelligence
An application of a merit function for solving convex programming problems

Computers and Industrial Engineering
Neural network for nonsmooth pseudoconvex optimization with general constraints

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper develops a project neural network for solving degenerate quadratic programming problems with general linear constraints. Compared with the existing neural networks for solving strict convex quadratic program, the proposed neural networks for solving degenerate convex quadratic program has a wider domain for implementation. In the theoretical aspects, the proposed neural network is shown to have complete convergence and finite-time convergence. Moreover, the nonsingular part of the output trajectory respect to Q has an exponentially convergent rate. Furthermore, through any equilibrium point of the proposed neural network, the information that whether the objective function can reach its minimum of R^n within the constraint conditions can be obtained easily. Illustrative examples further show the correctness of the results in this paper, and the good performance of the proposed neural network.