Porovnat metody

	Online Few-shot Learning	Učení s malým počtem příkladů
Obor	Strojové učení	Strojové učení
Rodina	Machine learning	Machine learning
Rok vzniku	2019	2011–2017
Tvůrce	Finn, C. et al. (online meta-learning formalization)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Typ	Online learning + meta-learning hybrid	Meta-learning / low-data learning paradigm
Původní zdroj	Finn, C., Rajeswaran, A., Kakade, S., & Levine, S. (2019). Online Meta-Learning. Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, 1920–1930.	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.
Další názvy	online meta-learning, streaming few-shot learning, continual few-shot learning, incremental few-shot learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Příbuzné	4	4
Shrnutí	Online Few-shot Learning combines the streaming update principle of online learning with the data-efficiency goal of few-shot learning, enabling a model to continuously adapt to new tasks or classes from only a handful of labeled examples as data arrives sequentially — without access to the full historical dataset.	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.