Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Apprentissage par transfert× | Apprentissage semi-supervisé× | |
|---|---|---|
| Domaine | Apprentissage automatique | Apprentissage automatique |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2010 (formalized); 1990s (early roots) | 1970s–2006 (formalized) |
| Auteur d'origine≠ | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| Type | Learning paradigm | Learning paradigm |
| Source fondatrice≠ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| Alias | TL, domain adaptation, fine-tuning, pre-trained model adaptation | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| Apparentées≠ | 3 | 5 |
| Résumé≠ | 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. | Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained. |
| ScholarGateJeu de données ↗ |
|
|