Metraipolis › archive › dc_beef7c889e61
Residual neural network — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Residual_neural_network
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-06T13:39:42.873Z
- SHA-256 of the archived text
11976a8a42bf6a08e1b99dad6998bc78b6816854bab4adb3f3c4233fb17c4cb0- Stable URL of this page
https://metraipolis.com/documento/dc_beef7c889e61
How to cite
Residual neural network — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Residual_neural_network (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_beef7c889e61 (Metraipolis archive dc_beef7c889e61, sha256 11976a8a42bf6a08e1b99dad6998bc78b6816854bab4adb3f3c4233fb17c4cb0)
BibTeX
@misc{dcbeef7c889e61,
title = {Residual neural network — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Residual_neural_network},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_beef7c889e61; sha256 11976a8a42bf6a08e1b99dad6998bc78b6816854bab4adb3f3c4233fb17c4cb0},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Residual_neural_network. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A residual neural network (also referred to as a residual network or ResNet) is a deep learning architecture in which the layers learn residual functions with reference to the layer inputs. It was developed in 2015 for image recognition, and won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) of that year. As a point of terminology, "residual connection" refers to the specific architectural motif of x ↦ f ( x ) + x {\displaystyle x\mapsto f(x)+x} , where f {\displaystyle f} is an arbitrary neural network module. The motif had been used previously (see §History for details). However, the publication of ResNet made it widely popular for feedforward networks, appearing in neural networks that are seemingly unrelated to ResNet. The residual connection stabilizes the training and convergence of deep neural networks with hundreds of layers, and is a common motif in deep neural networks, such as transformer models (e.g., BERT, and GPT models such as ChatGPT), the AlphaGo Zero system, the AlphaStar system, and the AlphaFold system.
Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «computer vision»).
Fonte: Wikipedia in inglese, voce «Residual neural network» — https://en.wikipedia.org/wiki/Residual_neural_network
Wikidata Q43744058: «type of artificial neural network» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q43744058
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Residual_neural_network?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1376425875, consultata il 2026-10-06T11:56:22.061Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: f1844790ce712da5f5a4928804153faecaa2c0fdad423a014bc92743cc2f993e