Abstract
In this paper first order 2D cellular neural networks (CNN’s) with homogeneous weight structure are investigated. It is proved that all CNN’s are divided into equivalence classes by respect to formed patterns properties. The method of learning first order CNN is proposed, which allows to find the parameters of CNN weight template if an example of stable state is given.
Supported by RFBR, grants 00-01-00026, 01-01-06261
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Simons N.R., Briges G.E., Cuhaci M.A: lattice gas automaton capable of modeling tree-dimensional Electromagnetic Fields.-Journ. of Computational Physics 151, 1999, pp. 816–835.
Leon O. Chua: CNN: a Paradigm for Complexity. World Scientific, Series on Nonlinear Science, Vol. 31, 1998.
Thiran P., Crounse K., Chua L.O., Hasler M.: Pattern Formation Properties of Autonomous Cellular Neural Networks. IEEE trans. on circ. and syst.-1: fund, theory and appl., vol. 42, NO. 10, October 1995.
Bandman O.L.: Cellular-Neural Computations, Formal Model and Possible Appli-cations. Lecture Notes in Computer Science, 964, 1995, p. 21–35.
Chua L.O., Yang L.: Cellular Neural Networks: Theory and Application. IEEE Trans. Circuits and Systems, CAS-35, 1257–1290 (1988).
Pudov S.: Learning of Cellular Neural Networks. Future Gen. Comp. Syst. 17 (2001), pp. 689–697.
Rosenblatt F.: Principles of Neurodynamics. Washington, Spartan, 1959.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pudov, S. (2001). First-Order 2D Cellular Neural Networks Investigation and Learning. In: Malyshkin, V. (eds) Parallel Computing Technologies. PaCT 2001. Lecture Notes in Computer Science, vol 2127. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44743-1_9
Download citation
DOI: https://doi.org/10.1007/3-540-44743-1_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42522-9
Online ISBN: 978-3-540-44743-6
eBook Packages: Springer Book Archive