On The Universality of The Single-Layer Perceptron Model

  • Šarūnas Raudys
Part of the Advances in Soft Computing book series (AINSC, volume 19)


The Single Layer Perceptron (SLP) calculates a weighted sum of numerous inputs and produces output as a smooth non-linear two side bounded function of this sum. We show that this simple mathematical model, originally proposed to consider the information processing in brain cells, features much more universal principles. If appropriately trained, the SLP can implement many commonly known statistical classification and regression algorithms. The SLP training and retraining can be used to model aging processes in technology, biology and society. The SLP model can be utilized to simulate continuous and turbulent wave propagation in excitable medias.


Cost Function Refractory Period Excitable Media Training Vector Noise Injection 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McCulloch W.S. and Pitts W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5: 115–33MathSciNetMATHCrossRefGoogle Scholar
  2. 2.
    Rumelhart D.E., Hinton G.E., Williams R.J. (1986). Learning internal representations by error propagation. In: Rumelhart D.E., McClelland J.L. (Eds.), Parallel Distributed Processing: Explorations in the microstructure of cognition. Bradford Books, Cambridge, MA I: 318–62Google Scholar
  3. 3.
    Widrow B. and Hoff M.E. (1960). Adaptive switching circuits. WESCON Convention Record, 4: 96–104Google Scholar
  4. 4.
    Raudys. (1998). Evolution and generalization of a single neurone. I. SLP as seven statistical classifiers. Neural Networks, 11 (2): 283–296CrossRefGoogle Scholar
  5. 5.
    Raudys. (2000). Evolution and generalization of a single neurone. III. Primitive, regularized, standard, robust and minimax regressions. Neural Networks, 13: 507–523CrossRefGoogle Scholar
  6. 6.
    Raudys. (2001). Statistical and Neural Classifiers: An integrated approach to design. Springer. London.MATHCrossRefGoogle Scholar
  7. 7.
    Raudys. (2002). An adaptation model for simulation of aging process. Int. J. of Modern Physics C ( 2002, accepted)Google Scholar
  8. 8.
    Thomsen O. and Kettel K. (1927). Die Starke der menschlichen Isoagglutinine und entsprechende Blutkorperchenreceptoren in vershiedenen Lebensaltern. Z. Immunitatsforsch., 63: 67–93Google Scholar
  9. 9.
    Makinodan T. and Yunis E., Eds. (1977). Immunololgy and Aging. Plenum Medical Book Company, New York & London.Google Scholar
  10. 10.
    Vinson M., Mironov S., Mulvey S., Pertsov A. (1997). Control of spatial orientation and lifetime of scroll rings in excitable media. Nature, 3886 (3): 477–480.CrossRefGoogle Scholar
  11. 11.
    Henriquez C.S. and Papazoglou A.A. (1996). Using computer models to understand the roles of tissue structure and membrane dynamics in arrhythmogenesis. Proceedings of the IEEE, 84 (3): 334–354CrossRefGoogle Scholar
  12. 12.
    Raudys. (2002). Neural network models of wave propagation in excitable media. Proc. of TASTED Im’. Conf. on Modelling, Identification and Control MIC’2002, Feb. 1821, 2002. Innsbruck, Austria (Hamra M.H. ed.). Acta Press. Anaheim, Calgary: 352–357Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Šarūnas Raudys
    • 1
  1. 1.Institute of Mathematics and InformaticsVilniusLithuania

Personalised recommendations