Abstract
Multistability and multiperiodicity of neual networks are usually considered in the application of associative memory. In this paper, we study the multistability and multiperiodicity of complex- valued neural networks (CVNNs for short) with one step piecewise linear activation functions. By separating the CVNN into its real and imaginary parts and using state decomposition, we can easily increase the storage capacity by using less neurons. Simulation results are given to illustrative the effectiveness of the theoretical results.
The work described in this paper was supported by the National Natural Science Foundation of China under Grants 61273021 and 61403051 and grants from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project nos. CUHK417209E and CUHK416811E).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bao, G., Zeng, Z.: Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions. Neurocomputing 77(1), 101–107 (2012)
Bohner, M., Rao, V.S.H., Sanyal, S.: Global stability of complex-valued neural networks on time scales. Differential Equations and Dynamical Systems 19(1–2), 3–11 (2011)
Cao, J., Feng, G., Wang, Y.: Multistability and multiperiodicity of delayed Cohen-Grossberg neural networks with a general class of activation functions. Physica D 237(13), 1734–1749 (2008)
Cheng, C., Lin, K., Shih, C.: Multistability in recurrent neural networks. SIAM Journal of Applied Mathematics 66(4), 1301–1320 (2006)
Di Marco, M., Forti, M., Grazzini, M., Pancioni, L.: Limit set dichotomy and multistability for a class of cooperative neural networks with delays. IEEE Transactions on Neural Networks and Learning Systems 23(9), 1473–1485 (2012)
Di Marco, M., Forti, M., Grazzini, M., Pancioni, L.: Convergent dynamics of nonreciprocal differential variational inequalities modeling neural networks. IEEE Transactions on Circuits and Systems I: Regular Papers 60(12), 3227–3238 (2013)
Duan, C., Song, Q.: Boundedness and stability for discrete-time delayed neural network with complex-valued linear threshold neurons. Discrete Dynamics in Nature and Society 2010, 1–19 (2010)
Hu, J., Wang, J.: Global stability of complex-valued recurrent neural networks with time-delays. IEEE Transcations on Neural Networks and Learning Systems 23(6), 853–865 (2012)
Jankowski, S., Lozowski, A., Zurada, J.: Complex-valued multistate neural associative memory. IEEE Transactions on Neural Networks 7(6), 1491–1496 (1996)
Kosaku, Y.: Functional Analysis. Springer, Berlin (1978)
Muezzinoglu, M.K., Guzelis, C., Zurada, J.M.: A new design method for the complex-valued multistate hopfield associative memory. IEEE Transactions on Neural Networks 14(4), 891–899 (2003)
Tanaka, G., Aihara, K.: Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction. IEEE Transactions on Neural Networks 20(9), 1463–1473 (2009)
Zeng, Z., Huang, T., Zheng, W.X.: Multistability of recurrent neural networks with time-varying delays and the piecewise linear activation function. IEEE Transcations on Neural Networks 21(8), 1371–1377 (2010)
Zeng, Z., Wang, J.: Multiperiodicity and exponential attractivity evoked by periodic external inputs in delayed cellular neural networks. Neural Computation 18(4), 848–870 (2006)
Zeng, Z., Wang, J., Liao, X.: Stability analysis of delayed cellular neural networks described using cloning templates. IEEE Transcations on Circuits and Systems-I:Regular Papers 51(11), 2313–2324 (2004)
Zhou, B., Song, Q.: Boundedness and complete stability of complex-valued neural networks with time delay. IEEE Transactions on Neural Networks and Learning Systems 24(8), 1227–1238 (2013)
Zhou, W., Zurada, J.M.: Discrete-time recurrent neural networks with complex-valued linear threshold neurons. IEEE Transactions on Circuits and Systems II: Express Briefs 56(8), 669–673 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Hu, J., Wang, J. (2014). Multistability and Multiperiodicity Analysis of Complex-Valued Neural Networks. In: Zeng, Z., Li, Y., King, I. (eds) Advances in Neural Networks – ISNN 2014. ISNN 2014. Lecture Notes in Computer Science(), vol 8866. Springer, Cham. https://doi.org/10.1007/978-3-319-12436-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-12436-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12435-3
Online ISBN: 978-3-319-12436-0
eBook Packages: Computer ScienceComputer Science (R0)