Sammenlign metoder

	Online læring	Few-shot Learning
Fagområde	Maskinlæring	Maskinlæring
Familie	Machine learning	Machine learning
Oprindelsesår	1958–2000s	2011–2017
Ophavsperson	Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Type	Learning paradigm (sequential model update)	Meta-learning / low-data learning paradigm
Oprindelig kilde	Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194.	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.
Aliasser	incremental learning, sequential learning, streaming learning, online machine learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Relaterede	6	4
Resumé	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.	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.