A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application

Authors:
Shuai Li;Yangming Li;Zheng Wang
Affiliations:
Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA;Robot Sensor and Human-Machine Interaction Lab, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, Anhui, China;Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON M5S3G4, Canada
Venue:
Neural Networks
Year:
2013

Citing 16
Cited 1

Finite-Time Stability of Continuous Autonomous Systems

SIAM Journal on Control and Optimization
Neural Networks for Combinatorial Optimization: a Review of More Than a Decade of Research

INFORMS Journal on Computing
A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations

Neural Networks
2008 Special Issue: Two k-winners-take-all networks with discontinuous activation functions

Neural Networks
A compact cooperative recurrent neural network for computing general constrained L1norm estimators

IEEE Transactions on Signal Processing
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 novel neural dynamical approach to convex quadratic program and its efficient applications

Neural Networks
Inter-modality mapping in robot with recurrent neural network

Pattern Recognition Letters
Noise-Robust Automatic Speech Recognition Using a Predictive Echo State Network

IEEE Transactions on Audio, Speech, and Language Processing
Decentralized kinematic control of a class of collaborative redundant manipulators via recurrent neural networks

Neurocomputing
A dual neural network for kinematic control of redundant robotmanipulators

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

IEEE Transactions on Neural Networks
A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limits

IEEE Transactions on Neural Networks
A Simplified Dual Neural Network for Quadratic Programming With Its KWTA Application

IEEE Transactions on Neural Networks
An Improved Dual Neural Network for Solving a Class of Quadratic Programming Problems and Its -Winners-Take-All Application

IEEE Transactions on Neural Networks
Finite-Time Convergent Recurrent Neural Network With a Hard-Limiting Activation Function for Constrained Optimization With Piecewise-Linear Objective Functions

IEEE Transactions on Neural Networks

From different ZFs to different ZNN models accelerated via Li activation functions to finite-time convergence for time-varying matrix pseudoinversion

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a class of recurrent neural networks to solve quadratic programming problems. Different from most existing recurrent neural networks for solving quadratic programming problems, the proposed neural network model converges in finite time and the activation function is not required to be a hard-limiting function for finite convergence time. The stability, finite-time convergence property and the optimality of the proposed neural network for solving the original quadratic programming problem are proven in theory. Extensive simulations are performed to evaluate the performance of the neural network with different parameters. In addition, the proposed neural network is applied to solving the k-winner-take-all (k-WTA) problem. Both theoretical analysis and numerical simulations validate the effectiveness of our method for solving the k-WTA problem.