Сравнение методов

	Байесовское обучение с малым числом примеров (Bayesian Few-Shot Learning)	Обучение на малом числе примеров (Few-shot Learning)
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2018-2019	2011–2017
Автор метода	Gordon et al.; Finn, Xu & Levine	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Тип	Probabilistic meta-learning	Meta-learning / low-data learning paradigm
Основополагающий источник	Gordon, J., Bronskill, J., Bauer, M., Nowozin, S. & Turner, R. E. (2019). Meta-Learning Probabilistic Inference for Prediction. International Conference on Learning Representations (ICLR 2019).	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.
Другие названия	Bayesian meta-learning, probabilistic few-shot learning, amortized Bayesian few-shot learning, Bayesian FSL	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Связанные	5	4
Сводка	Bayesian few-shot learning combines Bayesian inference with meta-learning to enable a model to generalize from as few as one to five labeled examples per class. By treating task-specific parameters as random variables and learning an informative prior across many training tasks, the method produces calibrated uncertainty estimates alongside predictions — a key advantage over deterministic few-shot learners.	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.