Advertisement

Analysis of the DNN-kWTA Network Model with Drifts in the Offset Voltages of Threshold Logic Units

  • Ruibin Feng
  • Chi-Sing LeungEmail author
  • John Sum
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9950)

Abstract

The structure of the dual neural network-based (DNN) k-winner-take-all (kWTA) model is much simpler than that of other kWTA models. Its convergence time and capability under the perfect condition were reported. However, in the circuit implementation, the threshold levels of the threshold logic units (TLUs) in the DNN-kWTA model may have some drifts. This paper analyzes the DNN-kWTA model under the imperfect condition, where there are some drifts in the threshold level. We show that given that the inputs are uniformly distributed in the range of [0, 1], the probability that the DNN-kWTA model gives the correct output is greater than or equal to \((1-2\varDelta )^n\), where \(\varDelta \) is the maximum drift level. Besides, we derive the formulas for the average convergent time and the variance of the convergent time under the drift situation.

Keywords

Winner-take-all Dual neural network Threshold logic unit Convergence 

References

  1. 1.
    Lazzaro, J., Ryckebusch, S., Mahowald, M.A., Mead, M.A.: Winner-take-all networks of O(N) complexity. In: Advances in Neural Information Processing Systems, vol. 1, pp. 703–711 (1989)Google Scholar
  2. 2.
    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 Netw. 10, 64–71 (1999)CrossRefGoogle Scholar
  3. 3.
    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 Trans. Neural Netw. 19, 2022–2031 (2008)CrossRefGoogle Scholar
  4. 4.
    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. Neural Netw. 21(9), 1496–1506 (2010)CrossRefGoogle Scholar
  5. 5.
    Xiao, Y., Liu, Y., Leung, C.-S., Sum, J., Ho, K.: Analysis on the convergence time of dual neural network-based. IEEE Trans. Neural Netw. Learn. Syst. 23(4), 676–682 (2012)CrossRefGoogle Scholar
  6. 6.
    Leung, C.-S., Sum, J.: A fault tolerant regularizer for RBF networks. IEEE Trans. Neural Netw. 19(3), 493–507 (2008)CrossRefGoogle Scholar
  7. 7.
    Wang, L.: Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks. IEEE Trans. Syst. Man Cybern. Part B Cybern. 27(5), 868–870 (1997)CrossRefGoogle Scholar
  8. 8.
    Hu, M., Li, H., Wu, Q., Rose, G.S., Chen, Y.: Memristor crossbar based hardware realization of BSB recall function. In: Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN) (2012)Google Scholar
  9. 9.
    He, J., Zhan, S., Chen, D., Geiger, R.L.: Analyses of static and dynamic random offset voltages in dynamic comparators. IEEE Trans. Circuits Syst. I 56(5), 911–919 (2009)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Sum, J., Leung, C.-S., Ho, K.: Effect of input noise and output node stochastic on Wang’s \(k\)WTA. IEEE Trans. Neural Netw. Learn. Syst. 24(9), 1472–1478 (2013)CrossRefGoogle Scholar
  11. 11.
    Bowling, S.R., Khasawneh, M.T., Kaewkuekool, S., Cho, B.R.: A logistic approximation to the cumulative normal distribution. J. Ind. Eng. Manag. 2(1), 114–127 (2009)Google Scholar
  12. 12.
    Arnold, B.C., Balakrishnan, N., Nagaraja, H.N.: A First Course in Order Statistics (Classics in Applied Mathematics). SIAM (2008)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Department of Electronic EngineeringCity University of Hong KongKowloon TongHong Kong
  2. 2.Institute of Technology ManagementNational Chung Hsing University TaichungTaichungTaiwan

Personalised recommendations