Sammenlign metoder

	Online Few-shot Learning	Online læring
Fagområde	Maskinlæring	Maskinlæring
Familie	Machine learning	Machine learning
Oprindelsesår	2019	1958–2000s
Ophavsperson	Finn, C. et al. (online meta-learning formalization)	Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors)
Type	Online learning + meta-learning hybrid	Learning paradigm (sequential model update)
Oprindelig kilde	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.	Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194.
Aliasser	online meta-learning, streaming few-shot learning, continual few-shot learning, incremental few-shot learning	incremental learning, sequential learning, streaming learning, online machine learning
Relaterede	4	6
Resumé	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.	Online learning is a machine learning paradigm in which a model is updated incrementally as each new data point arrives, rather than being trained once on a fixed dataset. It is essential when data streams continuously, storage is limited, or the underlying distribution shifts over time. Theoretical performance is measured by cumulative regret relative to the best fixed predictor in hindsight.