A Novel Recurrent Neural Network With One Neuron and Finite-Time Convergence for $k$-Winners-Take-All Operation

2010 ◽  
Vol 21 (7) ◽  
pp. 1140-1148 ◽  
Author(s):  
Qingshan Liu ◽  
Chuangyin Dang ◽  
Jinde Cao
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Finite Time ◽  
Finite Time Convergence ◽  
Take All

A Novel Recurrent Neural Network with Finite-Time Convergence for Linear Programming

2010 ◽  
Vol 22 (11) ◽  
pp. 2962-2978 ◽  
Author(s):  
Qingshan Liu ◽  
Jinde Cao ◽  
Guanrong Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Programming ◽  
Recurrent Neural Network ◽  
Finite Time ◽  
Lyapunov Method ◽  
Optimal Solutions ◽  
Excellent Performance ◽  
Finite Time Convergence ◽  
Linear Programming Problems

In this letter, a novel recurrent neural network based on the gradient method is proposed for solving linear programming problems. Finite-time convergence of the proposed neural network is proved by using the Lyapunov method. Compared with the existing neural networks for linear programming, the proposed neural network is globally convergent to exact optimal solutions in finite time, which is remarkable and rare in the literature of neural networks for optimization. Some numerical examples are given to show the effectiveness and excellent performance of the new recurrent neural network.

Sign in / Sign up

Export Citation Format

Share Document