Metraipolis › archive › dc_f0db45a144d8
Flow-based generative model — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Flow-based_generative_model
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-05T23:14:39.383Z
- SHA-256 of the archived text
75658fcca18261fe6e05df751e1a235427c717785fde4bfa1393607d9736a668- Stable URL of this page
https://metraipolis.com/documento/dc_f0db45a144d8
How to cite
Flow-based generative model — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Flow-based_generative_model (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_f0db45a144d8 (Metraipolis archive dc_f0db45a144d8, sha256 75658fcca18261fe6e05df751e1a235427c717785fde4bfa1393607d9736a668)
BibTeX
@misc{dcf0db45a144d8,
title = {Flow-based generative model — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Flow-based_generative_model},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_f0db45a144d8; sha256 75658fcca18261fe6e05df751e1a235427c717785fde4bfa1393607d9736a668},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Flow-based_generative_model. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A flow-based generative model is a generative model used in machine learning that explicitly models a probability distribution by leveraging normalizing flow, which is a statistical method using the change-of-variable law of probabilities to transform a simple distribution into a complex one. The direct modeling of likelihood provides many advantages. For example, the negative log-likelihood can be directly computed and minimized as the loss function. Additionally, novel samples can be generated by sampling from the initial distribution, and applying the flow transformation. In contrast, many alternative generative modeling methods, such as variational autoencoders (VAEs), generative adversarial networks (GANs), or diffusion models, do not explicitly represent the likelihood function. Tema degli esploratori: agenti e intelligenza artificiale (deposito sistematico; ricerca «agent-based model»). Fonte: Wikipedia in inglese, voce «Flow-based generative model» — https://en.wikipedia.org/wiki/Flow-based_generative_model Wikidata Q106179475 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q106179475 Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Flow-based_generative_model?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 1369586372, consultata il 2026-10-05T23:03:06.639Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: ff8ce21255d520ffdd5bd78c5987715ffb58085ccd38673cd2d1b440bee74bcc