Multi-valued neurons: Learning, networks, application to image recognition and extrapolation of temporal series

  • Naum N. Aizenberg
  • Igor N. Aizenberg
  • Georgy A. Krivosheev
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)


In this paper we consider in the developing conception of multi-valued neurons. First of all significant reinforcement of the learning algorithm which led to the 20–30 — times acceleration of the convergence of learning is proposed. Then neural network based on multi-valued neurons where each neuron is connected with restricted number of other ones (function of connections is defined as random function) is considered. Application of such an network to image recognition is proposed. Then approach to extrapolation of the temporal series based on the representation of the series as multiple-valued function, learning of the single neural element and furtheron forecasting of the function's values is also considered.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    N.N. Aizenberg Multiple-Valued Threshold Logic. Kiev: Naukova Dumka Publisher House (1977) (in Russian).Google Scholar
  2. [2]
    N.N.Aizenberg, I.N.Aizenberg: CNN Based on Multi-Valued Neuron as a Model of Associative Memory for Gray-Scale Images, Proc. of the 2-d International IEEE Workshop on Cellular Neural Networks and their Applications. Munich, Germany, October 14–16 (1992) IEEE 92TH0498-6, ISBN 0-7803-875-1, pp. 36–41.Google Scholar
  3. [3]
    N.N. Aizenberg, I.N. Aizenberg “Fast Convergenced Learning Algorithms for Multi-Level and Universal Binary Neurons and Solving of the some Image Processing Problems”, Lecture Notes in Computer Science, Ed.-J. Mira, J. Cabestany, A. Prieto, v.686, Shpringer-Verlag, Berlin-Heidelberg (1993) pp. 230–236.Google Scholar
  4. [4]
    N.N. Aizenberg, I.N. Aizenberg “Neural Networks based on Universal and Multi-Valued Neurons and their application to solving of the some problems of Image Processing and Pattern recognition”, Proc. of the “COST 229” Int. Workshop on Adaptive Systems, Intelligent Approaches, Massively Parallel Computing and Emergent Techniques in Signal Processing and Communications”, Bayona (Vigo), (1994) Publication of the University of Vigo and Politec. de Madrid, pp. 223–228.Google Scholar
  5. [5]
    T.Kohonen “Content-Addressable Memories” Springer-Verlag, Berlin-Heidelberg-New-York, 980.Google Scholar
  6. [6]
    U.Ramaher, W.Raab, J.Anlauf, U.Hachmann, J.Beichter, N.Bruls, M.Weseling, E.Sichender, R.Manner, J.Glass, A.Wurz “Multiprocessor and Memory Architecture of the Neurocomputer Synapse-1” Proceedings of the 3-d International Conference on Microelectronics for Neural Networks. April 6–8, 1993, Edinburgh, UK, pp. 227–231.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Naum N. Aizenberg
    • 1
  • Igor N. Aizenberg
    • 2
  • Georgy A. Krivosheev
    • 3
  1. 1.University of UzhgorodUzhgorodUkraine
  2. 2.Company “INFORM RTG Ltd”UzhgorodUkraine
  3. 3.Company “INFORM RTG Ltd”MoscowRussia

Personalised recommendations