Skip to main content
SpringerLink
Log in

Backpropagation

  • Reference work entry
Encyclopedia of Machine Learning

Synonyms

Backprop; BP; Generalized delta rule

Definition

Backpropagation of error (henceforth BP) is a method for training feed-forward neural networks see Artificial Neural Networks. A specific implementation of BP is an iterative procedure that adjusts network weight parameters according to the gradient of an error measure. The procedure is implemented by computing an error value for each output unit, and by backpropagating the error values through the network.

Characteristics

Feed-Forward Networks

A feed-forward neural network is a mathematical function that is composed of constituent “semi-linear” functions constrained by a feed-forward network architecture, wherein the constituent functions correspond to nodes (often called units or artificial neurons) in a graph, as in Fig. 1. A feedfoward network architecture has a connectivity structure that is an acyclic graph; that is, there are no closed loops.

Backpropagation. Figure 1
figure 1_51 figure 1_51

Two networks are shown. Input units are shown as simple...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Recommended Reading

  • Demers, D., & Cottrell, G. (1993). Non-linear dimensionality reduction. In S. J. Hanson, J. D. Cowan, & C. L. Giles (Eds.), Advances in neural information processing systems (Vol. 5). San Mateo, CA: Morgan Kaufmann.

    Google Scholar 

  • Elman, J. (1990). Finding structure in time. Cognitive Science, 14, 179–211.

    Google Scholar 

  • Minsky, M. L., & Papert, S. A. (1969). Perceptrons. Cambridge, MA: MIT Press.

    MATH  Google Scholar 

  • Pineda, F. J. (1989). Recurrent backpropagation and the dynamical approach to adaptive neural computation. Neural Computation, 1, 161–172.

    Google Scholar 

  • Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65, 386–408.

    MathSciNet  Google Scholar 

  • Rosenblatt, F. (1962). Principles of statistical neurodynamics. Washington, DC: Spartan.

    Google Scholar 

  • Werbos, P. (1974). Beyond regression: New tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard University, Cambridge.

    Google Scholar 

Download references

Author information

Authors and Affiliations

    Authors
    1. Paul Munro
      View author publications

      You can also search for this author in PubMed Google Scholar

    Editor information

    Editors and Affiliations

    1. School of Computer Science and Engineering, University of New South Wales, Sydney, Australia, 2052

      Claude Sammut

    2. Faculty of Information Technology, Clayton School of Information Technology, Monash University, P.O. Box 63, Victoria, Australia, 3800

      Geoffrey I. Webb

    Rights and permissions

    Reprints and permissions

    Copyright information

    © 2011 Springer Science+Business Media, LLC

    About this entry

    Cite this entry

    Munro, P. (2011). Backpropagation. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_51

    Download citation

    Publish with us

    Policies and ethics

    Search

    Navigation