Advertisement

A Continuous-Time Model of Analogue K-Winners-Take-All Neural Circuit

  • Pavlo V. Tymoshchuk
Part of the Communications in Computer and Information Science book series (CCIS, volume 311)

Abstract

A continuous-time model of analogue K-winners-take-all (KWTA) neural circuit which is capable to extraction the K largest from any finite value N unknown distinct inputs, where 1 ≤ K < N, is presented. The model is described by one state equation with discontinuous right-hand side and output equation. A corresponding functional block diagram of the model is given as N feedforward and one feedback hardlimiting neurons, which is used to determine the dynamic shift of inputs. The model combines such properties as high accuracy and convergence speed, low computational and hardware implementation complexity, and independency on initial conditions. Simulation examples demonstrating the model performance are provided.

Keywords

Continuous-time model State equation Functional block-diagram Hardlimiting neuron Analogue K-winners-take-all neural circuit 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    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 Publishers Inc., San Francisco (1989)Google Scholar
  2. 2.
    Atkins, M.: Sorting by Hopfield nets. In: IEEE Int. Joint Conf. on Neural Networks, pp. 65–68. IEEE Press (1982)Google Scholar
  3. 3.
    Urahama, K., Nagao, T.: K-winners-take-all circuit with 0(N) complexity. IEEE Trans. on Neural Networks 6, 776–778 (1995)CrossRefGoogle Scholar
  4. 4.
    Kwon, T.M., Zervakis, M.: KWTA networks and their applications. Multidimensional Syst. and Signal Processing 6, 333–346 (1995)zbMATHCrossRefGoogle Scholar
  5. 5.
    Binh, L.N., Chong, H.C.: A neural-network contention controller for packet switching networks. IEEE Trans. on Neural Networks 6, 1402–1410 (1995)CrossRefGoogle Scholar
  6. 6.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 20, 1254–1259 (1998)CrossRefGoogle Scholar
  7. 7.
    Cilingiroglu, U., Dake, T.L.E.: Rank-order filter design with a sampled-analog multiple-winners-take-all core. IEEE Journal on Solid-State Circuits 37, 978–984 (2002)CrossRefGoogle Scholar
  8. 8.
    Erlanson, R., Abu-Mostafa, Y.: Analog neural networks as decoders. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 1, pp. 585–588. Morgan Kaufmann Publishers Inc., San Francisco (1991)Google Scholar
  9. 9.
    Fish, A., Akselrod, D., Yadid-Pecht, O.: High precision image centroid computation via an adaptive k-winner-take-all circuit in conjunction with a dynamic element matching algorithm for star tracking applications. Analog Integrated Circuits and Signal Processing 39, 251–266 (2004)CrossRefGoogle Scholar
  10. 10.
    Jain, B.J., Wysotzki, F.: Central clustering of attributed graphs. Machine Learning 56, 169–207 (2004)zbMATHCrossRefGoogle Scholar
  11. 11.
    Liu, S., Wang, J.: A simplified dual neural network for quadratic programming with its KWTA application. IEEE Trans. on Neural Networks 17(6), 1500–1510 (2006)CrossRefGoogle Scholar
  12. 12.
    DeSouza, G.N., Zak, A.C.: Vision for mobile robot navigation: a survey. IEEE Trans. on Pattern Analysis and Machine Intelligence 24, 237–267 (2002)CrossRefGoogle Scholar
  13. 13.
    Graupe, D.: Principles of Artificial Neural Networks, 2nd edn. World Sci. Publisher, Singapore (2007)zbMATHGoogle Scholar
  14. 14.
    Cichocki, A., Unbehauen, R.: Neural Networks for Optimization and Signal Processing. John Wiley & Sons, Chichester (1993)zbMATHGoogle Scholar
  15. 15.
    Wang, J.: Analysis and design of a k-winners-take-all model with a single state variable and the Heaviside step activation function. IEEE Trans. on Neural Networks 9, 1496–1506 (2010)CrossRefGoogle Scholar
  16. 16.
    Tymoshchuk, P.V.: A dynamic K-winners take all analog neural circuit. In: IVth IEEE Int. Conf. “Perspective Technologies and Methods in MEMS Design”, pp. 13–18. IEEE Press, L’viv (2008)Google Scholar
  17. 17.
    Liu, Q., Wang, J.: Two k-winners-take-all networks with discontinuous activation functions. Neural Networks 21, 406–413 (2008)zbMATHCrossRefGoogle Scholar
  18. 18.
    Tymoshchuk, P.V.: Stability analysis of continuous-time model of K-Winners-Take-All neural circuit. In: XVI Ukrainian-Polish Conf. “CAD in Machinery Design. Implementation and Educational Problems”, pp. 29–30. IEEE Press, L’viv (2008)Google Scholar
  19. 19.
    Tymoshchuk, P.V.: A discrete-time dynamic K-winners-take-all neural circuit. Neurocomputing 72, 3191–3202 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pavlo V. Tymoshchuk
    • 1
    • 2
  1. 1.EIT DepartmentLodz UniversityLodzPoland
  2. 2.CAD DepartmentL’viv Polytechnic National UniversityL’vivUkraine

Personalised recommendations