Comparer des méthodes

	Apprentissage bayésien à peu d'exemples	Apprentissage par transfert
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2018-2019	2010 (formalized); 1990s (early roots)
Auteur d'origine	Gordon et al.; Finn, Xu & Levine	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Type	Probabilistic meta-learning	Learning paradigm
Source fondatrice	Gordon, J., Bronskill, J., Bauer, M., Nowozin, S. & Turner, R. E. (2019). Meta-Learning Probabilistic Inference for Prediction. International Conference on Learning Representations (ICLR 2019).	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Alias	Bayesian meta-learning, probabilistic few-shot learning, amortized Bayesian few-shot learning, Bayesian FSL	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Apparentées	5	3
Résumé	Bayesian few-shot learning combines Bayesian inference with meta-learning to enable a model to generalize from as few as one to five labeled examples per class. By treating task-specific parameters as random variables and learning an informative prior across many training tasks, the method produces calibrated uncertainty estimates alongside predictions — a key advantage over deterministic few-shot learners.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.