Metraipolis › archive › dc_59fe1f2c65fc
Batch normalization — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Batch_normalization
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-07T20:11:14.519Z
- SHA-256 of the archived text
c9153b5f329a60199b468b69c8930e29c661ccdbaf591c9df302d03292c78599- Stable URL of this page
https://metraipolis.com/documento/dc_59fe1f2c65fc
How to cite
Batch normalization — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Batch_normalization (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_59fe1f2c65fc (Metraipolis archive dc_59fe1f2c65fc, sha256 c9153b5f329a60199b468b69c8930e29c661ccdbaf591c9df302d03292c78599)
BibTeX
@misc{dc59fe1f2c65fc,
title = {Batch normalization — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Batch_normalization},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_59fe1f2c65fc; sha256 c9153b5f329a60199b468b69c8930e29c661ccdbaf591c9df302d03292c78599},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Batch_normalization. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable by adjusting the inputs to each layer—re-centering them around zero and re-scaling them to a standard size. It was introduced by Sergey Ioffe and Christian Szegedy in 2015. Experts still debate why batch normalization works so well. It was initially thought to tackle internal covariate shift, a problem where parameter initialization and changes in the distribution of the inputs of each layer affect the learning rate of the network. However, newer research suggests it does not fix this shift but instead smooths the objective function—a mathematical guide the network follows to improve—enhancing performance. In very deep networks, batch normalization can initially cause a severe gradient explosion—where updates to the network grow uncontrollably large—but this is managed with shortcuts called skip connections in residual networks. Another theory is that batch normalization adjusts data by handling its size and path separately, speeding up training. Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «artificial neural network»). Fonte: Wikipedia in inglese, voce «Batch normalization» — https://en.wikipedia.org/wiki/Batch_normalization Wikidata Q55080248 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q55080248 Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Batch_normalization?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 1375137441, consultata il 2026-10-07T19:25:58.284Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: a1de94b70f0cfdc16037217a277a096b826e3d934b869b53c045378e6ba9a631