A general methodology for designing globally convergent optimization neural networks
- 1 November 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 9 (6), 1331-1343
- https://doi.org/10.1109/72.728383
Abstract
We present a general methodology for designing optimization neural networks. We prove that the neural networks constructed by using the proposed method are guaranteed to be globally convergent to solutions of problems with bounded or unbounded solution sets, in contrast with the gradient methods whose convergence is not guaranteed. We show that the proposed method contains both the gradient methods and nongradient methods employed in existing optimization neural networks as special cases. Based on the theoretical results of the proposed method, we study the convergence and stability of general gradient models in the case of unisolated solutions. Using the proposed method, we derive some new neural network models for a very large class of optimization problems, in which the equilibrium points correspond to exact solutions and there is no variable parameter. Finally, some numerical examples show the effectiveness of the method.Keywords
This publication has 31 references indexed in Scilit:
- Neural network for solving extended linear programming problemsIEEE Transactions on Neural Networks, 1997
- On solving systems of linear inequalities with artificial neural networksIEEE Transactions on Neural Networks, 1997
- A new neural network for solving linear programming problems and its applicationIEEE Transactions on Neural Networks, 1996
- Neural network for solving linear programming problems with bounded variablesIEEE Transactions on Neural Networks, 1995
- A deterministic annealing neural network for convex programmingNeural Networks, 1994
- On solving constrained optimization problems with neural networks: a penalty method approachIEEE Transactions on Neural Networks, 1993
- Linear and quadratic programming neural network analysisIEEE Transactions on Neural Networks, 1992
- Nonlinear switched capacitor 'neural' networks for optimization problemsIEEE Transactions on Circuits and Systems, 1990
- Neural networks for nonlinear programmingIEEE Transactions on Circuits and Systems, 1988
- Solution of symmetric linear complementarity problems by iterative methodsJournal of Optimization Theory and Applications, 1977