McCulloch's neurons revisited

  • Robert J. Scott
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 686)


The 1943 McCulloch and Pitts seminal paper on artificial neurons (ANs) provided the stimulus for early neural network research. However, McCulloch's work in the 50's has been mainly overlooked. The importance of this later work is shown in this paper not only because McCulloch's neuron design was significantly more powerful than either the Perception or the Adeline, but also because of its ability to satisfy the XOR function 12 years before the publication of Minsky and Papert's book, Perceptrons. The similarities between McCulloch's work in the 50's and 60's and more current AN research are also identified here. Some rudimentary experiments with AN design using a delta learning rule are also included. It is hoped that by recasting McCulloch's and the author's early work in terms of current technology, further research will be stimulated in designing efficient artificial neural systems that provide the stability and reliability of biological systems. These were the goals of McCulloch's original work.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    W.S. McCulloch and W. Pitts, “A Logical Calculus of the Ideas Immanent in Neural Activity,” Bulletin of Mathematical Biophysics, Vol. 5, pp. 115–133, 1943.Google Scholar
  2. [2]
    F. Rosenblatt, “The Perceptron: a Probabalistic Model for Information Storage and Organization in the Brain,” Psychological Review, 65, pp. 386–408, 1958.Google Scholar
  3. [3]
    M. Minsky and S. Papert, Perceptrons, MIT Press, Cambridge, MA, 1969.Google Scholar
  4. [4]
    R. Eberhart and R. Dobbins, Ed., Neural Network PC Tools, Academic Press, San Diego, CA, 1990.Google Scholar
  5. [5]
    M. Caudill and C. Butler, Naturally Intelligent Systems, MIT Press, Cambridge, MA, 1990.Google Scholar
  6. [6]
    W. Altman, Apprentices of Wonder, Bantam Books, New York, 1989.Google Scholar
  7. [7]
    W. McCulloch, “The Stability of Biological Systems,” Homeostatic Mechanisms, Brookhaven Symposia in Biology: No. 10, Uptown, NY, 1957.Google Scholar
  8. [8]
    J.E. Whitesitt, Boolean Algebra and its Applications, p. 33, Addison-Wesley Publishing Co., Reading, MA, 1961.Google Scholar
  9. [9]
    M. Minsky, Computation: Finite and Infinite Machines, Prentice-Hall, Inc., Englewood Cliffs, NJ, 1967.Google Scholar
  10. [10]
    N. Scott, Analog and Digital Computer Technology, McGraw-Hill Co., New York, 1960.Google Scholar
  11. [11]
    W. McCulloch, “What is a Number That a Man May Know it and a Man, That he May Know a Number?,” in W. McCulloch, Embodiments of Mind, MIT Press, Cambridge, MA, 1988.Google Scholar
  12. [12]
    R. Scott, “Construction of a Neuron Model,” IRE Transactions on Bio-Medical Electronics, Vol. BME 8, No.3, July, 1961.Google Scholar
  13. [13]
    N. Nilsson, The Mathematical Foundations of Learning Machines, Morgan Kaufman Publishers, San Mateo, CA, 1990.Google Scholar
  14. [14]
    R. Duda and P. Hart, Pattern Classification and Scene Analysis, Wiley, New York, 1973.Google Scholar
  15. [15]
    D. Rumelhart, G. Hinton, and R. Williams, “Learning Internal Representations by Error Propagation,” in D. Rumelhart and J. McClelland, Eds., Parallel Distributed Processing: Explorations in the Microstructures of Cognition, Vol. 1, MIT Press, Cambridge, MA, 1986.Google Scholar
  16. [16]
    T. Sejnowski, “Higher Ordered Boltzman Machines,” American Institute of Physics Conference Proceedings, No. 151, Neural Networks for Computing, pp. 398–403, Snowbird, UT, 1986.Google Scholar
  17. [17]
    M Klassen and Y. Pao, “Characteristics of the Functional-Link Net: A Higher Order Delta Rule Net,” IEEE Proceedings of the 2nd Annual International Conference on Neural Networks, San Diego, CA, June, 1988.Google Scholar
  18. [18]
    Y. Pao, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley Publishing Co., Reading, MA, 1989.Google Scholar
  19. [19]
    R. Goodman, C. Higgins, J. Miller, and P. Smyth, “Rule-Based Neural Networks for Classification and Probability Estimation,” Neural Computation, pp. 781–804, Vol. 4, No. 6, Nov, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Robert J. Scott
    • 1
  1. 1.Information Systems DepartmentThe University of Maryland Baltimore CountyBaltimoreUSA

Personalised recommendations