Metraipolis › archive › dc_4a3fa7fab261

Neural tangent kernel — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/Neural_tangent_kernel
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-06T13:40:57.102Z
SHA-256 of the archived text
99fa25c0a9d178b0e6610e6b4aa6b9d84291aecdc5072dd98ab8837e88e43963
Stable URL of this page
https://metraipolis.com/documento/dc_4a3fa7fab261

How to cite

Neural tangent kernel — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Neural_tangent_kernel (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_4a3fa7fab261 (Metraipolis archive dc_4a3fa7fab261, sha256 99fa25c0a9d178b0e6610e6b4aa6b9d84291aecdc5072dd98ab8837e88e43963)
BibTeX
@misc{dc4a3fa7fab261,
  title = {Neural tangent kernel — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Neural_tangent_kernel},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_4a3fa7fab261; sha256 99fa25c0a9d178b0e6610e6b4aa6b9d84291aecdc5072dd98ab8837e88e43963},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Neural_tangent_kernel. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In the study of artificial neural networks (ANNs), the neural tangent kernel (NTK) is a kernel that describes the evolution of deep artificial neural networks during their training by gradient descent. It allows ANNs to be studied using theoretical tools from kernel methods. In general, a kernel is a positive-semidefinite symmetric function of two inputs which represents some notion of similarity between the two inputs. The NTK is a specific kernel derived from a given neural network; in general, when the neural network parameters change during training, the NTK evolves as well. However, in the limit of large layer width the NTK becomes constant, revealing a duality between training the wide neural network and kernel methods: gradient descent in the infinite-width limit is fully equivalent to kernel gradient descent with the NTK. As a result, using gradient descent to minimize least-square loss for neural networks yields the same mean estimator as ridgeless kernel regression with the NTK. This duality enables simple closed form equations describing the training dynamics, generalization, and predictions of wide neural networks. The NTK was introduced in 2018 by Arthur Jacot, Franck Gabriel and Clément Hongler, who used it to study the convergence and generalization properties of fully connected neural networks. Later works extended the NTK results to other neural network architectures. In fact, the phenomenon behind NTK is not specific to neural networks and can be observed in generic nonlinear models, usually by a suitable scaling.

Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «artificial neural network»).
Fonte: Wikipedia in inglese, voce «Neural tangent kernel» — https://en.wikipedia.org/wiki/Neural_tangent_kernel
Wikidata Q85788335: «type of kernel in artificial neural networks» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q85788335
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Neural_tangent_kernel?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 1368847382, consultata il 2026-10-06T11:57:25.255Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 55c16aec98c993fa57c99189de9b7389993e85a2cf053396e370edba579702df