Abstract
A recurrent neural network is presented for solving systems of quadratic programming problems with equality constraints involving complex-valued coefficients. The proposed recurrent neural network is asymptotically stable and able to generate optimal solutions to quadratic programs with equality constraints. An opamp based analogue circuit realization of the recurrent neural network is described. An illustrative example is also discussed to demonstrate the performance and characteristics of the analogue neural network.
Chapter PDF
Similar content being viewed by others
References
Kennedy, M., Chua, L.O.: Neural Networks for Nonlinear Programming. IEEE Trans. CAS-35(5), 554–562 (1988)
Wang, J.: Recurrent Neural Network for Solving Quadtratic Propramming Problems with Equality Constraints. Electronics Letter 28(14), 345–1347 (1992)
Wudai, L., Jiangfeng, W.: A Lower Order Recurrent Neural Network for Solving Higher Order Quadratic Programming Problems with Equality Constraints. In: Proceedings of the Second International Joint Conference on Computational Sciences (CSO 2009), Sanya, Hainan, China, April 24-26, pp. 176–178 (2009), 978-0-7695-3605-7
Jun, W.: Electronic Realisation of Recurrent Neural Network for Solving Simultaneous Linear Equations. Electron Letters 28(5), 493–495 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liao, W., Wang, J., Wang, J. (2010). A Recurrent Neural Network for Solving Complex-Valued Quadratic Programming Problems with Equality Constraints. In: Tan, Y., Shi, Y., Tan, K.C. (eds) Advances in Swarm Intelligence. ICSI 2010. Lecture Notes in Computer Science, vol 6146. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13498-2_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-13498-2_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13497-5
Online ISBN: 978-3-642-13498-2
eBook Packages: Computer ScienceComputer Science (R0)