Neural network for quadratic optimization with bound constraints
- 1 March 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 4 (2), 293-304
- https://doi.org/10.1109/72.207617
Abstract
A recurrent neural network is presented which performs quadratic optimization subject to bound constraints on each of the optimization variables. The network is shown to be globally convergent, and conditions on the quadratic problem and the network parameters are established under which exponential asymptotic stability is achieved. Through suitable choice of the network parameters, the system of differential equations governing the network activations is preconditioned in order to reduce its sensitivity to noise and to roundoff errors. The optimization method employed by the neural network is shown to fall into the general class of gradient methods for constrained nonlinear optimization and, in contrast with penalty function methods, is guaranteed to yield only feasible solutions.Keywords
This publication has 18 references indexed in Scilit:
- Error in proof of exponential convergenceNeural Networks, 1992
- Exponential stability and a systematic synthesis of a neural network for quadratic minimizationNeural Networks, 1991
- IMPROVED NEURAL NETWORKS FOR LINEAR AND NONLINEAR PROGRAMMINGInternational Journal of Neural Systems, 1991
- Weight adjustment rule of neural networks for computing discrete 2-D Gabor transforms (image processing)IEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- Optimal preconditioners of a given sparsity patternBIT Numerical Mathematics, 1989
- Neural networks for nonlinear programmingIEEE Transactions on Circuits and Systems, 1988
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filtersJournal of the Optical Society of America A, 1985
- Two-dimensional spectral analysis of cortical receptive field profilesVision Research, 1980
- Stability theory for ordinary differential equationsJournal of Differential Equations, 1968