« Generative model » : différence entre les versions
Aller à la navigation
Aller à la recherche
Aucun résumé des modifications |
Aucun résumé des modifications |
||
| Ligne 1 : | Ligne 1 : | ||
« A generative model describes how a dataset is generated, in terms of a probabilistic model. By sampling from this model, we are able to generate new data. » | « A generative model describes how a dataset is generated, in terms of a probabilistic model. By sampling from this model, we are able to generate new data. » | ||
« A generative model must be probabilistic rather than deterministic. If our model is merely a fixed calculation, such as taking the average value of each pixel in the dataset, it is not generative because the model produces the same output every time. The model must include a stochastic (random) element that influences the individual samples generated by the model. » | |||
== Références == | == Références == | ||
Generative Deep Learning - David Foster - O'Reilly - 2019 | Generative Deep Learning - David Foster - O'Reilly - 2019 | ||
Version actuelle datée du 4 janvier 2023 à 09:13
« A generative model describes how a dataset is generated, in terms of a probabilistic model. By sampling from this model, we are able to generate new data. »
« A generative model must be probabilistic rather than deterministic. If our model is merely a fixed calculation, such as taking the average value of each pixel in the dataset, it is not generative because the model produces the same output every time. The model must include a stochastic (random) element that influences the individual samples generated by the model. »
Références
Generative Deep Learning - David Foster - O'Reilly - 2019