Advertisement

Artificial Neural Networks

  • Miroslav Kubat
Chapter

Abstract

Polynomial classifiers can model decision surfaces of any shape; and yet their practical utility is limited because of the easiness with which they overfit noisy training data, and because of the sometimes impractically high number of trainable parameters. Much more popular are artificial neural networks where many simple units, called neurons, are interconnected by weighted links into larger structures of remarkably high performance.

References

  1. 1.
    Ash, T. (1989). Dynamic node creation in backpropagation neural networks. Connection Science: Journal of Neural Computing, Artificial Intelligence, and Cognitive Research, 1, 365–375.CrossRefGoogle Scholar
  2. 12.
    Broomhead, D. S. & Lowe, D. (1988). Multivariable functional interpolation and adaptive networks. Complex Systems, 2, 321–355.MathSciNetzbMATHGoogle Scholar
  3. 13.
    Bryson, A. E. & Ho, Y.-C. (1969). Applied optimal control. New York: Blaisdell.Google Scholar
  4. 66.
    Minsky, M. & Papert, S. (1969). Perceptrons. Cambridge, MA: MIT.zbMATHGoogle Scholar
  5. 83.
    Rumelhart, D. E. & McClelland, J. L. (1986). Parallel distributed processing. Cambridge: MIT Bradford Press.Google Scholar
  6. 95.
    Werbos, P. (1974). Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD thesis, Harvard University.Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Miroslav Kubat
    • 1
  1. 1.Department of Electrical and Computer EngineeringUniversity of MiamiCoral GablesUSA

Personalised recommendations