Abstract
An interior point recurrent neural network for convex inequality constrained optimization problems is proposed, based on the logarithmic barrier function. A time varying barrier parameter is used and the network’s dynamical equations are based on Newton’s method. Strictly feasible interior point trajectories are produced which converge to the exact solution of the constrained problem as t → ∞. Numerical results for examples of various sizes show that the method is both efficient and accurate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barbarosou, M.P., Maratos, N.G.: A nonfeasible gradient projection recurrent neural network for equality-constrained optimization problems. IEEE Trans. Neural Netw. 19, 1665–1677 (2008)
Bazaraa, M.S., Sherali, H.D., Shetty, C.M.: Nonlinear Programming, Theory and Algorithms. Wiley, New York (1993)
Bouzerdoum, A., Pattison, T.: Neural network for quadratic optimization with bound constraints. IEEE Trans. Neural Netw. 4, 293–304 (1993)
Cichocki, A., Unbehauen, R.: Neural networks for optimization and signal processing. Wiley, New York (1993)
Kennedy, M.P., Chua, L.O.: Unifying the Tank and Hopfield linear programming circuit and the canonical nonlinear programming circuit of Chua and Lin. IEEE Trans. Circuits Syst. 34, 210–214 (1986)
Kennedy, M.P., Chua, L.O.: Neural networks for nonlinear programming. IEEE Trans. Circuits Syst. 35, 554–562 (1988)
Krasopoulos, P.T., Maratos, N.G.: A neural network for convex optimization. In: IEEE International Symposium on Circuits and Systems, pp. 747–750. Island of Kos, 21–24 May 2006
Leung, Y., Chen, K.-Z., Jiao, Y.-C., Gao, X.-B., Leung K.S.: A new gradient-based neural network for solving linear and quadratic programming problems. IEEE Trans. Neural Netw. 12, 1074–1083 (2001)
Leung, Y., Chen, K.-Z., Gao, X.-B.: A high-performance feedback neural network for solving convex nonlinear programming problems. IEEE Trans. Neural Netw. 14, 1469–1477 (2003)
Lillo, W.E., Loh, M.H., Hui, S., Zak, S.H.: On solving constrained optimization problems with neural networks: a penalty method approach. IEEE Trans. Neural Netw. 4, 931–940 (1993)
Luenberger, D.G.: Linear and Nonlinear Programming. Addison-Wesley, Reading (1984)
Sudharsanan, S., Sundareshan, M.: Exponential stability and a systematic synthesis of a neural network for quadratic minimization. Neural Netw. 4, 599–613 (1991)
Tank, D.W., Hopfield, J.J.: Simple “neural” optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans. Circuits Syst. 33, 533–541 (1986)
Xia, Y., Wang, J.: A recurrent neural network for solving linear projection equations. Neural Netw. 13, 337–350 (2000)
Xia, Y., Feng, G., Wang, J.: A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations. Neural Netw. 17, 1003–1015 (2004)
Zak, S.H., Upatising, V., Hui, S.: Solving linear programming problems with neural networks: a comparative study. IEEE Trans. Neural Netw. 6, 94–103 (1995)
Acknowledgements
The authors wish to thank Prof. Themistocles M. Rassias for his kind editorial hospitality. The first author would like to thank the National Scholarship Foundation of Greece (IKY) for financial support during the course of this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this chapter
Cite this chapter
Krasopoulos, P.T., Maratos, N.G. (2014). An Interior Point Recurrent Neural Network for Convex Optimization Problems. In: Pardalos, P., Rassias, T. (eds) Mathematics Without Boundaries. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-1124-0_13
Download citation
DOI: https://doi.org/10.1007/978-1-4939-1124-0_13
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4939-1123-3
Online ISBN: 978-1-4939-1124-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)