Un modèle génératif est un modèle qui apprend la distribution ou la structure des données d’entraînement afin de créer de nouveaux exemples ou d’estimer la vraisemblance d’exemples. Il peut générer du contenu, simuler des données ou prendre en charge des tâches telles que l’apprentissage de représentations et la détection d’anomalies.
Practically speaking, a model that does either of the following: - Creates (generates) new examples from the training dataset. For example, a generative model could create poetry after training on a dataset of poems. The generator part of a generative adversarial network falls into this category. - Determines the probability that a new example comes from the training set, or was created from the same mechanism that created the training set. For example, after training on a dataset consisting of English sentences, a generative model could determine the probability that new input is a valid English sentence. A generative model can theoretically discern the distribution of examples or particular features in a dataset. That is: Unsupervised learning models are generative. Contrast with discriminative models.
A type of machine learning model that can create novel outputs based on its training data. At its simplest, the model generates new data that looks like a certain set of categories that it was trained on. Usually associated with large language models, but other types of models can be generative as well.