Learning Representations by Back-propagating Errors

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning Representations by Back-propagating Errors. Nature, 323(6088), 533-536.

Type

Journal article

Intellectual base

Primary research

Year

1986

Volume

323

Issue

6088

Pages

533-536

DOI

10.1038/323533a0

DOI registrant

Springer Nature

Link

https://doi.org/10.1038/323533a0

Cited from

computer_science, mathematics

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Gradient
  • In optimization and machine learning, gradient descent and its stochastic variants (originating with Cauchy and revived for large-scale ML by Robbins-Monro), backpropagation
• Higher Order Function
  • In legal theory this maps to the hierarchy of norms; in machine learning, to the chain rule and backpropagation.

    This sourceBackpropagation as repeated application of the chain rule — composition over differentiable rules.

    Supported in partVerified against the publisher's abstract

    This paper's abstract introduces back-propagation as a machine-learning procedure, but it does not itself state the chain rule and says nothing about legal theory.

    “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.”

    Read by an automated reader; not a human review. How support was checked

Verification

Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.

Does it back the claim? Read against the text for 1 of 2 citations: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.

Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.

See how references were verified.

Registry ID ref:6f36c808f0f6 · see in the full table