Learning representations by back-propagating errors

  • Nature volume 323, pages 533536 (09 October 1986)
  • doi:10.1038/323533a0
  • Download Citation
Published online:


We describe a new learning procedure, back-propagation, for networks of neurone-like units. The procedure repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector. As a result of the weight adjustments, internal ‘hidden’ units which are not part of the input or output come to represent important features of the task domain, and the regularities in the task are captured by the interactions of these units. The ability to create useful new features distinguishes back-propagation from earlier, simpler methods such as the perceptron-convergence procedure1.

  • Subscribe to Nature for full access:



Additional access options:

Already a subscriber?  Log in  now or  Register  for online access.


  1. 1.

    Principles of Neurodynamics (Spartan, Washington, DC, 1961).

  2. 2.

    & Perceptrons (MIT, Cambridge, 1969).

  3. 3.

    Proc. Cognitiva 85, 599–604 (1985).

  4. 4.

    , & in Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. 1: Foundations (eds Rumelhart, D. E. & McClelland, J. L.) 318–362 (MIT, Cambridge, 1986).

Download references

Author information


  1. Institute for Cognitive Science, C-015, University of California, San Diego, La Jolla, California 92093, USA

    • David E. Rumelhart
    •  & Ronald J. Williams
  2. Department of Computer Science, Carnegie-Mellon University, Pittsburgh, Philadelphia 15213, USA

    • Geoffrey E. Hinton


  1. Search for David E. Rumelhart in:

  2. Search for Geoffrey E. Hinton in:

  3. Search for Ronald J. Williams in:


By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.