Advertisement

Models of Self-correlation Type Complex-Valued Associative Memories and Their Dynamics

  • Yasuaki Kuroe
  • Yuriko Taniguchi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)

Abstract

Associative memories are one of the popular applications of neural networks and several studies on their extension to the complex domain have been done. One of the important factors to characterize behavior of a complex-valued neural network is its activation function which is a nonlinear complex function. We have already proposed a model of self-correlation type associative memories using complex-valued neural networks with one of the most commonly used activation function. In this paper, we propose two additional models using different nonlinear complex functions and investigated their behaviors as associative memories theoretically. Comparisons are also made among these three models in terms of dynamics and storage capabilities.

Keywords

Equilibrium Point Activation Function Nonlinear Dynamical System Associative Memory Hadamard Matrice 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hirose, A.: Dynamics of fully complex-valued neural networks. Electronics Letters 28(16), 1492–1494 (1992)CrossRefGoogle Scholar
  2. 2.
    Kuroe, Y., Hashimoto, N., Mori, T.: Qualitative analysis of a self-correlation type complex-valued associative memories. Nonlinear Analysis 47, 5795–5806 Google Scholar
  3. 3.
    Kuroe, Y., Hashimoto, N., Mori, T.: Qualitative Analysis of Continuous Complex-Valued Associative Memories. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 843–850. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  4. 4.
    Nemoto, I., Kono, T.: Complex-valued neural network. The Trans. of IEICE J74-D-II (9), 1282–1288 (1991) (in Japanese)Google Scholar
  5. 5.
    Noest, A.J.: Phaser neural network. In: Anderson, D.Z. (ed.) Neural Informaion Processing Systems, pp. 584–591. AIP, New York (1988)Google Scholar
  6. 6.
    Jankowski, S., Lozowski, A., Zurada, J.M.: Complex-valued multistate neural associative memory. IEEE Trans. Neural Networks 7(6), 1491–1496 (1996)CrossRefGoogle Scholar
  7. 7.
    Georgiou, G.M., Koutsougeras, C.: Complex Domain Backpropagation. IEEE Transactions on Circuits and Systems-II 39(5), 330–334 (1992)zbMATHCrossRefGoogle Scholar
  8. 8.
    Kuroe, Y., Yoshida, M., Mori, T.: On Activation Functions for Complex-Valued Neural Networks - Existence of Energy Functions. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 985–992. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  9. 9.
    Sastry, S.: Nonlinear Systems Analysis, Stability, and Control. Springer, Heidelberg (1999)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Yasuaki Kuroe
    • 1
  • Yuriko Taniguchi
    • 2
  1. 1.Center for Information Science 
  2. 2.Department of Electronics and Information ScienceKyoto Institute of TechnologyKyotoJapan

Personalised recommendations