Advertisement

Pramana

, Volume 40, Issue 1, pp 35–42 | Cite as

On training feedforward neural networks

  • Subhash Kak
Article

Abstract

A new algorithm that mapsn-dimensional binary vectors intom-dimensional binary vectors using 3-layered feedforward neural networks is described. The algorithm is based on a representation of the mapping in terms of the corners of then-dimensional signal cube. The weights to the hidden layer are found by a corner classification algorithm and the weights to the output layer are all equal to 1. Two corner classification algorithms are described. The first one is based on the perceptron algorithm and it performs generalization. The computing power of this algorithm may be gauged from the example that the exclusive-Or problem that requires several thousand iterative steps using the backpropagation algorithm was solved in 8 steps. Another corner classification algorithm presented in this paper does not require any computations to find the weights. However, in its basic form it does not perform generalization.

Keywords

Neural networks nonlinear systems 87·30 64·60 75·10 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    D E Rumelhartet al Parallel distributed processing, (The MIT Press, Cambridge, 1986) Vol. 1Google Scholar
  2. [2]
    M L Minsky and S A Papert,Perceptrons, (The MIT Press, Cambridge, 1988)Google Scholar
  3. [3]
    S C Kak,Pramana - J. Phys.,38, 271 (1992)CrossRefADSGoogle Scholar
  4. [4]
    Rosenblatt, F,Principles of neurodynamics, (Spartan, New York, 1962)Google Scholar
  5. [5]
    S A Papert, Some mathematical models of learning.Proceedings of the fourth London symposium on information theory (1961)Google Scholar

Copyright information

© Indian Academy of Sciences 1993

Authors and Affiliations

  • Subhash Kak
    • 1
  1. 1.Department of Electrical and Computer EngineeringLouisiana State UniversityBaton RougeUSA

Personalised recommendations