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. In complex-valued neural networks, there are several possibilities in choosing an activation function because of a wide variety of complex functions. This paper proposes three models of orthogonal type dynamic associative memories using complex-valued neural networks with three different activation functions. We investigate their behavior as associative memories theoretically. Comparisons are also made among these three models in terms of dynamics and storage capabilities.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hirose, A.: Dynamics of fully complex-valued neural networks. Electronics Letters 28(16), 1492–1494 (1992)
Kuroe, Y., Hashimoto, N., Mori, T.: Qualitative analysis of a self-correlation type complex-valued associative memories. Nonlinear Analysis 47, 5795–5806
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)
Nemoto, I., Kono, T.: Complex-valued neural network ((in Japanese)). The Trans. of IEICE J74-D-II(9), 1282–1288 (1991)
Noest, A.J.: Phaser neural network. In: Anderson, D.Z. (ed.) Neural Informaion Processing Systems, pp. 584–591. AIP, New York (1988)
Jankowski, S., Lozowski, A., Zurada, J.M.: Complex-valued multistate neural associative memory. IEEE Trans. Neural Networks 7(6), 1491–1496 (1996)
Georgiou, G.M., Koutsougeras, C.: Complex Domain Backpropagation. IEEE Transactions on Circuits and Systems-II 39(5), 330–334 (1992)
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)
Kuroe, Y., Taniguchi, Y.: Models of Self-Correlation Type Complex-Valued Associative Memories and Their Dynamics. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 185–192. Springer, Heidelberg (2005)
Sastry, S.: Nonlinear Systems Analysis, Stability, and Control. Springer, Heidelberg (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuroe, Y., Taniguchi, Y. (2007). Models of Orthogonal Type Complex-Valued Dynamic Associative Memories and Their Performance Comparison. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4668. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74690-4_85
Download citation
DOI: https://doi.org/10.1007/978-3-540-74690-4_85
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74689-8
Online ISBN: 978-3-540-74690-4
eBook Packages: Computer ScienceComputer Science (R0)