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

Authors:
Qingshan Liu; Jun Wang
Affiliations:
Sch. of Autom., Southeast Univ., Nanjing, China;-
Venue:
IEEE Transactions on Neural Networks
Year:
2011

Citing 0
Cited 9

A one-layer dual recurrent neural network with a heaviside step activation function for linear programming with its linear assignment application

ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application

Neural Networks
The UPPAM continuous-time RNN model and its critical dynamics study

Neurocomputing
Generalized recurrent neural network for ε-insensitive support vector regression

Mathematics and Computers in Simulation
A finite-time convergent recurrent neural network based algorithm for the L smallest k-subsets sum problem

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
A projection neural network with mixed delays for solving linear variational inequality

Neurocomputing
A one-layer recurrent neural network for constrained nonsmooth invex optimization

Neural Networks
Neural network for nonsmooth pseudoconvex optimization with general constraints

Neurocomputing
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 one-layer recurrent neural network for solving a class of constrained nonsmooth optimization problems with piecewise-linear objective functions. The proposed neural network is guaranteed to be globally convergent in finite time to the optimal solutions under a mild condition on a derived lower bound of a single gain parameter in the model. The number of neurons in the neural network is the same as the number of decision variables of the optimization problem. Compared with existing neural networks for optimization, the proposed neural network has a couple of salient features such as finite-time convergence and a low model complexity. Specific models for two important special cases, namely, linear programming and nonsmooth optimization, are also presented. In addition, applications to the shortest path problem and constrained least absolute deviation problem are discussed with simulation results to demonstrate the effectiveness and characteristics of the proposed neural network.