“Learning representations by back-propagating errors”

E11117

landmark paper in machine learning research article scientific paper

“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

AI illustration

All labels observed (2)

Label	Occurrences
Learning representations by back-propagating errors	2
“Learning representations by back-propagating errors” canonical	1

How this entity was disambiguated

This entity first appeared as the object of triple T93175 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: “Learning representations by back-propagating errors”
Context triple: [Geoffrey Hinton, notableWork, “Learning representations by back-propagating errors”]

A. Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
B. Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
C. Lifelong Learning Machines program
The Lifelong Learning Machines program is a DARPA research initiative aimed at developing AI systems that can continuously learn and adapt from experience in dynamic, real-world environments.
D. SyNAPSE neuromorphic computing program
The SyNAPSE neuromorphic computing program is a DARPA initiative to develop brain-inspired electronic systems that emulate neural architectures for highly efficient, scalable cognitive computing.
E. Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: “Learning representations by back-propagating errors”
Target entity description: “Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.

A. Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
B. Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
C. Lifelong Learning Machines program
The Lifelong Learning Machines program is a DARPA research initiative aimed at developing AI systems that can continuously learn and adapt from experience in dynamic, real-world environments.
D. SyNAPSE neuromorphic computing program
The SyNAPSE neuromorphic computing program is a DARPA initiative to develop brain-inspired electronic systems that emulate neural architectures for highly efficient, scalable cognitive computing.
E. Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
F. None of above. chosen

Statements (40)

Predicate	Object
instanceOf	landmark paper in machine learning ⓘ research article ⓘ scientific paper ⓘ
algorithmType	gradient-based learning algorithm ⓘ
author	David E. Rumelhart ⓘ Geoffrey E. Hinton ⓘ linked to: Geoffrey Hinton Ronald J. Williams ⓘ
citationStatus	highly cited paper in machine learning ⓘ
contribution	demonstrated that internal representations can be learned by gradient descent ⓘ popularized backpropagation for training multi-layer neural networks ⓘ showed that distributed representations can solve complex pattern recognition tasks ⓘ
era	connectionist revival of the 1980s ⓘ
field	artificial intelligence ⓘ deep learning ⓘ machine learning ⓘ neural networks ⓘ
focus	learning internal hidden-unit representations ⓘ training feedforward neural networks ⓘ
historicalSignificance	helped launch the modern field of deep learning ⓘ
influencedField	computer vision ⓘ deep learning ⓘ natural language processing ⓘ speech recognition ⓘ
language	English ⓘ
learningParadigm	error backpropagation ⓘ
mainTopic	backpropagation algorithm ⓘ multi-layer neural networks ⓘ representation learning ⓘ supervised learning ⓘ
method	chain rule of calculus for error propagation ⓘ gradient descent on error function ⓘ
networkType	multi-layer perceptron ⓘ
publicationYear	1986 ⓘ
publishedIn	Nature ⓘ
publisher	Nature Publishing Group ⓘ
relatedAlgorithm	backpropagation ⓘ
relatedConcept	credit assignment problem ⓘ distributed representations ⓘ gradient-based optimization ⓘ
title	Learning representations by back-propagating errors ⓘ linked to: “Learning representations by back-propagating errors”

How these facts were elicited

Referenced by (3)

Full triples — surface form annotated when it differs from this entity's canonical label.

Geoffrey Hinton → notableWork → “Learning representations by back-propagating errors” ⓘ

Learning representations by back-propagating errors → title → Learning representations by back-propagating errors ⓘ

subject linked to: “Learning representations by back-propagating errors”

linked to: “Learning representations by back-propagating errors”

David E. Rumelhart → notableWork → Learning representations by back-propagating errors ⓘ