Nature 323, 533 - 536 (09 October 1986); doi:10.1038/323533a0

Learning representations by back-propagating errors

David E. Rumelhart^*, Geoffrey E. Hinton^† & Ronald J. Williams^*

^*Institute for Cognitive Science, C-015, University of California, San Diego, La Jolla, California 92093, USA
^†Department of Computer Science, Carnegie-Mellon University, Pittsburgh, Philadelphia 15213, USA
^†To whom correspondence should be addressed.

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.

References

1.	Rosenblatt, F. Principles of Neurodynamics (Spartan, Washington, DC, 1961).
2.	Minsky, M. L. & Papert, S. Perceptrons (MIT, Cambridge, 1969).
3.	Le Cun, Y. Proc. Cognitiva 85, 599−604 (1985).
4.	Rumelhart, D. E., Hinton, G. E. & Williams, R. J. 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).