Athena
TR
Technology / inventionBranches2012

Deep learning

Geoffrey HintonYann LeCunYoshua BengioAlex KrizhevskyIlya Sutskever

This page delivers no verdict; it presents claims and evidence with their sources. No theory in science is absolute. Method

For everyone

Artificial neural networks, inspired by nerve cells in the brain, had been studied since the 1950s. In 2012 a many-layered ("deep") network trained on graphics processors beat earlier methods in image recognition by a wide margin, an event regarded as the start of today's wave of AI. Hinton and Hopfield received the 2024 Nobel Prize in Physics for foundational contributions to the field.

For specialists

AlexNet cut the top-5 error on ImageNet 2012 from about 26% to 15.3%, using convolutional layers trained on GPUs with ReLU activations and dropout. Back-propagation (Rumelhart, Hinton, Williams 1986) and convolutional networks (LeCun 1989) had been developed earlier. The ability of deep networks to generalise, even when large enough to memorise, is not fully explained theoretically.

Claims

Evidence

Supporting

Measurement

In ImageNet 2012 the deep convolutional network achieved an error rate about 10 points lower than the next best method.[1]

Challenging

Experiment

It was shown that tiny changes to an image, imperceptible to humans, can make deep networks misclassify it.[3]

Connections

Parent

Computing and artificial intelligence

Built upon by

AlphaFold and protein structure predictionThe Transformer and large language models

This topic is a stop on these journeys

From counting to artificial intelligence · stop 9/11

Show in tree →

Sources

  1. ArticleKrizhevsky, A.; Sutskever, I.; Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM 60(6), 84–90 (originally NeurIPS 2012)DOI 10.1145/3065386archive
  2. ArticleLeCun, Y.; Bengio, Y.; Hinton, G. (2015). Deep learning. Nature 521, 436–444DOI 10.1038/nature14539archive
  3. PreprintSzegedy, C. et al. (2014). Intriguing properties of neural networksarXiv:1312.6199archive

Search the literature

Look for scholarly work on this topic in other indexes:

Google Scholar ↗Semantic Scholar ↗BASE ↗CORE ↗arXiv ↗DergiPark ↗

Cite this page

APA

Athena contributors. (2026). Deep learning. Athena: The tree of human knowledge. Retrieved November 1, 2026, from https://latifkedi.github.io/athena/en/d/derin-ogrenme/

BibTeX
@misc{athena_derin_ogrenme,
  title        = {Deep learning},
  author       = {{Athena contributors}},
  year         = {2026},
  howpublished = {\url{https://latifkedi.github.io/athena/en/d/derin-ogrenme/}},
  note         = {Athena: The tree of human knowledge. Accessed: 2026-11-01}
}

Added: September 27, 2026 · Last changed: September 27, 2026 · Page history

✎ Suggest a correction