Abstract
It is considered the static and dynamic analysis of an analog electrical circuit having the structure of the Hopfield neural network, the KWTA (K-Winners-Take-All) network. The mathematics of circuit design and operation is discussed via two basic tools: the Liapunov function ensuring the gradient like behavior and the rational choice of the weights that stands for network training to ensure order-preserving trajectories. Dynamics and behavior at equilibria are considered in their natural interaction, and some connections to the ideas in general dynamical systems of convolution type are suggested.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Brockett, R.W.: Dynamical systems that sort lists, diagonalize matrices and solve linear programming problems. Lin. Algeb. Applicat. 146, 79–91 (1991)
Calvert, B.D., Marinov, C.A.: Another k-winners-take-all analog neural network. IEEE Trans. Neural Networks 11, 829–838 (2000)
Danciu, D.: Dynamics of Neural Networks as Nonlinear Systems with Several Equilibria. In: Porto, A.B., Pazos, A., Buno, W. (eds.) Advancing Artificial Intelligence through Biological Process Applications, pp. 331–357. Medical Information Science Reference, London (2008)
Danciu, D., Răsvan, V.: Stability results for cellular neural networks with time delays. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 366–373. Springer, Heidelberg (2005)
Danciu, D., Răsvan, V.: Dynamics of neural networks - some qualitative properties. In: Sandoval, F., Prieto, A.G., Cabestany, J., Graña, M. (eds.) IWANN 2007. LNCS, vol. 4507, pp. 8–15. Springer, Heidelberg (2007)
Danciu, D., Răsvan, V.: Neural Networks - Equilibria, Synchronization, Time Lags. In: Rabunal, J.R., Dorado, J., Pazos, A. (eds.) Encyclopedia of Artificial Intelligence. Information Science Reference, pp. 1219–1225. Idea Group, London (2008)
Drăgan, V., Halanay, A.: Stabilization of linear systems. Birkhäuser, Basel (1999)
Majani, E., Erlanson, R., Abu Mostafa, Y.: On the K-winners-take-all network. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 1, pp. 634–642. Morgan Kaufmann, San Mateo (1989)
Marinov, C.A.: Dynamical systems modelling computational circuits. Math. Reports 9(59), 55–60 (2007)
Popov, V.M.: Monotonicity and Mutability. Journ. Diff. Eqs. 31, 337–358 (1979)
Răsvan, V.: Dynamical systems with several equilibria and natural Liapunov functions. Archivum mathematicum (Brno) 34, 207–215 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Danciu, D., Răsvan, V. (2009). Gradient Like Behavior and High Gain Design of KWTA Neural Networks. In: Cabestany, J., Sandoval, F., Prieto, A., Corchado, J.M. (eds) Bio-Inspired Systems: Computational and Ambient Intelligence. IWANN 2009. Lecture Notes in Computer Science, vol 5517. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02478-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-02478-8_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02477-1
Online ISBN: 978-3-642-02478-8
eBook Packages: Computer ScienceComputer Science (R0)