A discontinuous recurrent neural network with predefined time convergence for solution of linear programming
Cargando...
Fecha
2014-12-09
Autores
Loukianov, Alexander
Sánchez-Torres, Juan D.
Sánchez-Camperos, Edgar
Título de la revista
ISSN de la revista
Título del volumen
Editor
Institute of Electrical and Electronics Engineers
Resumen
Descripción
The aim of this paper is to introduce a new recurrent neural network to solve linear programming. The main characteristic of the proposed scheme is its design based on the predefined-time stability. The predefined-time stability is a stronger form of finite-time stability which allows the a priori definition of a convergence time that does not depend on the network initial state. The network structure is based on the Karush-Kuhn-Tucker (KKT) conditions and the KKT multipliers are proposed as sliding mode control inputs. This selection yields to an one-layer recurrent neural network in which the only parameter to be tuned is the desired convergence time. With this features, the network can be easily scaled from a small to a higher dimension problem. The simulation of a simple example shows the feasibility of the current approach.
Palabras clave
Recurrent Neural Networks, Linear Programming, Predefined-time Stability
Citación
Sánchez-Torres, J.D.; Sánchez, E.N.; Loukianov, A.G., "A discontinuous recurrent neural network with predefined time convergence for solution of linear programming,"Swarm Intelligence (SIS), 2014 IEEE Symposium on, Orlando, USA, Dec. 2014, pp.1,5, 9-12.