×

Trust region method in neural network. (English) Zbl 0885.68127

Summary: A Hopfield-type neural network with adaptively changing synaptic weights and activation function parameters is presented to solve unconstrained nonlinear programming problems. The network performance is similar to that of the trust region method in the mathematical programming literature. There is a sub-network to solve quadratic programming problems with simple upper and lower bounds. By sequentially activating the sub-network under the control of an external computer or a special analog or digital processor that adjusts the weights and parameters, the network solves a sequence of unconstrained nonlinear programming problems. Convergence proof and numerical results are given.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
90C30 Nonlinear programming
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] A. Bouzerdoum and T.R. Pattison. Neural Network for Quadratic Optimization with Bound Constraints.IEEE Trans. Neural Networks, 1993, 4: 293–304. · doi:10.1109/72.207617
[2] L.O. Chua and G.-N. Lin. Nonlinear Programming without Computation.IEEE Trans. Circuits Syst., 1984, CAC-31(2): 182–188. · doi:10.1109/TCS.1984.1085482
[3] J.C. Culioli, V. Protopopescu, C.L. Britton and M.N. Ericson. Neural Networks Models for Linear Programming.Proc. IJCCN, 1990, 1: 293–296.
[4] J.J. Hopfield. Neurons with Graded Response Have Collective Computational Properties Like Those of Two-state Neurons.Proc. of Natural Academic Science, USA, 1984, 81: 3088–3092. · Zbl 1371.92015 · doi:10.1073/pnas.81.10.3088
[5] J.J. Hopfield and D.W. Tank. Neural Computation of Decision in Optimization Problems.Biological Cybernetics, 1985, 52: 141–152. · Zbl 0572.68041
[6] M.P. Kennedy and L.O. Chua. Neural Networks for Nonlinear Programming.IEEE Trans. Circuits Syst., 1988, 35: 554–562. · doi:10.1109/31.1783
[7] Lasalle. The Stability of Dynamical Systems. J.W. Arrowsmith Ltd., 1976. · Zbl 0364.93002
[8] C.Y. Maa and M.A. Shanblatt. Linear and Quadratic Programming Neural Network Analysis.IEEE Trans. Neural Networks, 1992, 3: 380–394.
[9] S. Osowski. Neural Network for Non-linear Programming with Linear Equality Constraints.International J. of Circuit Theory and Applications, 1992, 20: 93–98. · doi:10.1002/cta.4490200108
[10] A. Rodriguez-vázquez, R. Domingguez-castro, A. Rueda, J.L. Huertas and E. Sánchez-sinencio. Non-linear Switched-capacitor ”Neural” Networks for Optimization Problems.IEEE Trans. Circuits Syst., 1990, 37: 384–398. · doi:10.1109/31.52732
[11] D.W. Tank and J.J. Hopfield. Simple Neural Optimization Networks: An A/D Converter, Signal Decision Network and a Linear Programming Circuit.IEEE Trans. Circuits Syst., 1986, 33: 533–541. · doi:10.1109/TCS.1986.1085953
[12] B. Widrow and M.E. Jr. Hoff. Adaptive Switching Circuits. 1960 IRE Western Electric Show and Convention Record, Part 4, pp.96–104, 1960.
[13] B. Widrow and M.A. Lehr. 30 Years of Adaptive Neural Networks: Perceptron, Adaline and Back-propagation.Proc. IEEE, 1990, 78(9): 1415–1442. · doi:10.1109/5.58323
[14] Y. Xia and J. Wang. Neural Network for Solving Linear Programming Problem with Bound Variables.IEEE Trans. Neural Networks, 1995, 6: 515–519. · doi:10.1109/72.363493
[15] Y. Xia. A New Neural Network for Solving Linear Programming and Its Application.IEEE Trans. Neural Networks, 1996, 7(2): 525–529. · doi:10.1109/72.485686
[16] Y.-X. Yuan. Trust Region Algorithms for Nonlinear Programming.Contemporary Mathematics, 1994, 163: 205–225. · Zbl 0807.65063
[17] S.H. Zak, V. Upatising and S. Hui. Solving Linear Programming Problems with Neural Networks: A Comparative Study.IEEE Trans. Neural Networks, 1995, 6: 94–104. · doi:10.1109/72.363446
[18] S. Zhang and A.G. Constantinides. Lagrange Programming Neural Networks.IEEE Trans. Circuits Syst. II, 1992, 39(7): 441–452. · Zbl 0758.90067 · doi:10.1109/82.160169
[19] S. Zhang, X. Zhu and L. Zou. Secon-order Neural Network for Constrained Optimization.IEEE Trans. Neural Networks, 1992, 3(3): 1021–1023. · doi:10.1109/72.165605
[20] X.S. Zhang and H.C. Zhu. A Neural Network Model for Quadratic Programming with Simple Upper and Lower Bounds and Its Application to Linear Programming. Algorithms and Computation, Lecture Notes in Computer Science 834, pp. 119–127, Springer-Verlag, 1994. · Zbl 0953.90562
[21] X.S. Zhang. Mathematical Analysis for Some Neural Networks for Solving Linear and Quadratic Programming.Acta Mathematicae Applicatae Sinica, 1996, 12(1): 1–10. · Zbl 0856.90079 · doi:10.1007/BF02009555
[22] A. Torn and A. Zilinskas. Global Optimization. Lecture Notes in Computer Science, Vol.350, Springer-Verlag, 1989.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.