The Evolution of a Feedforward Neural Network trained under Backpropagation

  • D. McLean
  • Z. Bandar
  • J. D. O’Shea
Conference paper


This paper presents a theoretical and empirical analysis of the evolution of a feedforward neural network (FFNN) trained using backpropagation (BP). The results of two sets of experiments axe presented which illustrate the nature of BP’s search through weight space as the network learns to classify the training data. The search is shown to be driven by the initial values of the weights in the output layer of neurons.


Output Layer Feedforward Neural Network Weight Space Random Weight Initialisation Random Neural Network 
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]
    S.E. Fahlman. Faster-learning variations on BP: An empirical study. In D. Touretszky, G. Hinton, and T. Sejinowski, editors, Proceedings of the 1988 Connectionist Models Summer School, pages 38–51, 1989.Google Scholar
  2. [2]
    R.A. Jacobs. Increased rates of convergence through learning rate adaptation. Neural Networks, 1:295–307, 1988.CrossRefGoogle Scholar
  3. [3]
    D. Rumelhart, G. Hinton, and R. Williams. Learning representations by BP errors. Letters to Nature, 323:533–535, 1996.CrossRefGoogle Scholar
  4. [4]
    I.K. Sethi. Entropy nets: From decision trees to neural networks. Proceedings of the IEEE, 78(10):1605–1613, 1990.Google Scholar
  5. [5]
    H. Sompolinsky and A. Crisanti. Chaos in random neural networks. Physical Review Letters, 61(3):259–262, 1988.MathSciNetCrossRefGoogle Scholar
  6. [6]
    P.F.M.J. Verschure. Chaos-based learning. Complex Systems, 5:359–370, 1991.MATHGoogle Scholar

Copyright information

© Springer-Verlag Wien 1998

Authors and Affiliations

  • D. McLean
    • 1
  • Z. Bandar
    • 1
  • J. D. O’Shea
    • 1
  1. 1.The Intelligent Systems GroupThe Manchester Metropolitan UniversityManchesterUK

Personalised recommendations