Abstract
This paper presents an analog neural network model to recover sparse signals. In the original constrained optimization task for recovering sparse signals, the objective function is not differentiable. Hence, we recast the original nonlinear programming problem as a linear programming problem with linear inequality constraints and equality constraints. However, the second order gradient of the objective function is not convex at an equilibrium point. To solve this problem, we further modify the objective function such that the second order gradient is convex at the equilibrium point. This paper presents two sets of network dynamics. One is for the standard recovery of sparse signals. Another one is for the noisy situation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Candès, E.J., Wakin, M.B.: An introduction to compressive sampling. IEEE Signal Processing 25(1), 21–30 (2008)
Coifman, R., Geshwind, F., Meyer, Y.: Noiselets. Applied and Computational Harmonic Analysis 10, 27–44 (2001)
Tank, D.W., Hopfield, J.J.: Simple neural optimization networks: An AD converter, signal decision circuit, and a linear programming circuit. IEEE Trans. Circuits and Systems 33, 533–541 (1986)
Culioli, J.C., Protopopescu, V., Britton, C.L., Ericson, M.N.: Neural networks models for linear programming. In: Proc. IJCNN, vol. 1, pp. 293–296 (1990)
Chua, L., Lin, G.: Nonlinear programming without computation. IEEE Trans. on Circuits Syst. 31, 182–188 (1984)
Liu, S., Wang, J.: A Simplified Dual Neural Network for Quadratic Programming With Its KWTA Application. IEEE Transactions on Neural Networks 17(6), 1500–1510 (2006)
Hu, X., Wang, J.: An Improved Dual Neural Network for Solving a Class of Quadratic Programming Problems and Its k-Winners-Take-All Application. IEEE Transactions on Neural Networks 19(12), 2022–2031 (2008)
Sum, J., Leung, C.S., Tam, P., Young, G., Kan, W., Chan, L.W.: Analysis for a class of winner-take-all model. IEEE Trans. Neural Networks 10(1), 64–71 (1999)
Zhang, S., Constantinidies, A.G.: Lagrange programming neural networks. IEEE Trans. on Circuits and Systems II 39, 441–452 (1992)
Zhu, X., Constantinidies, A.G.: Lagrange programming neural networks for Linear Programming. Journal of Parallel and Distributed Computing 14, 354–360 (1993)
Kosko, B.: Bidirectional associative memories. IEEE Trans. Syst. Man Cybern. 18(1), 49–60 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leung, CS., Sum, J.PF., Lam, PM., Constantinides, A.G. (2011). Recovery of Sparse Signal from an Analog Network Model. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24965-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-24965-5_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24964-8
Online ISBN: 978-3-642-24965-5
eBook Packages: Computer ScienceComputer Science (R0)