Comparer des méthodes

	Apprentissage par transfert bayésien	Apprentissage à peu d'exemples
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2006–2010	2011–2017
Auteur d'origine	Raina, R.; Ng, A. Y.; Koller, D. (and subsequent community)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Type	Probabilistic transfer / domain adaptation framework	Meta-learning / low-data learning paradigm
Source fondatrice	Raina, R., Ng, A. Y., & Koller, D. (2006). Constructing informative priors using transfer learning. In Proceedings of the 23rd International Conference on Machine Learning (ICML), pp. 713–720. ACM.	Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29.
Alias	BTL, Bayesian domain adaptation, probabilistic transfer learning, Bayesian knowledge transfer	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Apparentées	4	4
Résumé	Bayesian Transfer Learning is a probabilistic framework that uses knowledge from a data-rich source domain to construct informative priors for a model trained on a data-scarce target domain. By encoding source-domain knowledge as prior distributions over parameters, the framework lets the model generalize well on the target task even with very limited labeled examples.	Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.