A Recurrent Neural Network for Solving Nonlinear Convex Programs Subject to Linear Constraints
- 7 March 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 16 (2), 379-386
- https://doi.org/10.1109/tnn.2004.841779
Abstract
In this paper, we propose a recurrent neural network for solving nonlinear convex programming problems with linear constraints. The proposed neural network has a simpler structure and a lower complexity for implementation than the existing neural networks for solving such problems. It is shown here that the proposed neural network is stable in the sense of Lyapunov and globally convergent to an optimal solution within a finite time under the condition that the objective function is strictly convex. Compared with the existing convergence results, the present results do not require Lipschitz continuity condition on the objective function. Finally, examples are provided to show the applicability of the proposed neural network.Keywords
This publication has 21 references indexed in Scilit:
- A General Projection Neural Network for Solving Monotone Variational Inequalities and Related Optimization ProblemsIEEE Transactions on Neural Networks, 2004
- A One-Layer Recurrent Neural Network for Support Vector Machine LearningIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2004
- A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limitsIEEE Transactions on Neural Networks, 2003
- A projection neural network and its application to constrained optimization problemsIEEE Transactions on Circuits and Systems I: Regular Papers, 2002
- A high performance neural network for solving nonlinear programming problems with hybrid constraintsPhysics Letters A, 2001
- On the Stability of Globally Projected Dynamical SystemsJournal of Optimization Theory and Applications, 2000
- A recurrent neural network for nonlinear optimization with a continuously differentiable objective function and bound constraintsIEEE Transactions on Neural Networks, 2000
- A Lagrangian network for kinematic control of redundant robot manipulatorsIEEE Transactions on Neural Networks, 1999
- A general methodology for designing globally convergent optimization neural networksIEEE Transactions on Neural Networks, 1998
- Support-vector networksMachine Learning, 1995