Neurocomputing with time delay analysis for solving convex quadratic programming problems
Authors:
- Yen-Hung ChenYCYen-Hung Chen
- Shu-Cherng FangSFShu-Cherng Fang
- 1 January 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 11 (1) , 230-240
Abstract
This paper presents a neural-network computational scheme with time-delay consideration for solving convex quadratic programming problems. Based on some known results, a delay margin is explicitly determined for the stability of the neural dynamics, under which the states of the neural network does not oscillate. The configuration of the proposed neural network is provided. Operational characteristics of the neural network are demonstrated via numerical examples.Keywords
This publication has 30 references indexed in Scilit:
- Brief communication Periodic solutions and stability of Hopfield neural networks with variable delaysInternational Journal of Systems Science, 1996
- Global exponential stability and periodic solutions of delay Hopfield neural networksInternational Journal of Systems Science, 1996
- Gradient calculations for dynamic recurrent neural networks: a surveyIEEE Transactions on Neural Networks, 1995
- Solving linear programming problems with neural networks: a comparative studyIEEE Transactions on Neural Networks, 1995
- Stability of nonlinear analytic delay equationsInternational Journal of Systems Science, 1994
- A deterministic annealing neural network for convex programmingNeural Networks, 1994
- Nonlinear Optimization Using Generalized Hopfield NetworksNeural Computation, 1989
- Stability of x(t)=Ax(t)+Bx(t- tau )IEEE Transactions on Automatic Control, 1989
- The Linear Quadratic Control Problem for Infinite Dimensional Systems with Unbounded Input and Output OperatorsSIAM Journal on Control and Optimization, 1987
- On an estimate of the decay rate for stable linear delay systemsInternational Journal of Control, 1982