Сравнение методов

	Байесовское обучение с малым числом примеров (Bayesian Few-Shot Learning)	Перенос обучения
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2018-2019	2010 (formalized); 1990s (early roots)
Автор метода	Gordon et al.; Finn, Xu & Levine	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Probabilistic meta-learning	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).	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Другие названия	Bayesian meta-learning, probabilistic few-shot learning, amortized Bayesian few-shot learning, Bayesian FSL	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Связанные	5	3
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.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.