Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Učení s malým počtem příkladů× | Semisupervisední učení× | |
|---|---|---|
| Obor | Strojové učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2011–2017 | 1970s–2006 (formalized) |
| Tvůrce≠ | Lake, B. M.; Vinyals, O.; Finn, C. et al. | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| Typ≠ | Meta-learning / low-data learning paradigm | Learning paradigm |
| Původní zdroj≠ | 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. link ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| Další názvy | FSL, low-shot learning, k-shot learning, meta-learning for few examples | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| Příbuzné≠ | 4 | 5 |
| Shrnutí≠ | 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. | 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. |
| ScholarGateDatová sada ↗ |
|
|