Learning hidden representations by back-propagation

What changed

Demonstrated how propagating output errors backward can adjust weights in multilayer networks and learn useful internal representations from examples.

Scientific scope

The 1986 demonstration and exposition of learning hidden representations by back-propagated errors.

Evidence

Original sources and institutional historical accounts support the stated contribution. The reading boundary is recorded at each source; this assessment is not an independent scientific verification.

Contributors

• David E. Rumelhart · SCIENCE: Named source contributor to this scoped work; individual labor shares are not measured.
• Geoffrey E. Hinton · SCIENCE: Named source contributor to this scoped work; individual labor shares are not measured.
• Ronald J. Williams · SCIENCE: Named source contributor to this scoped work; individual labor shares are not measured.

• Rumelhart, Hinton and Williams, Learning Representations by Back-Propagating Errors, Nature 323, 533–536 (1986)

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction