Сравнение методов

	Активное обучение	Мультизадачное обучение	Перенос обучения
Область	Машинное обучение	Глубокое обучение	Машинное обучение
Семейство	Machine learning	Machine learning	Machine learning
Год появления	2009	1997	2010 (formalized); 1990s (early roots)
Автор метода	Burr Settles	Rich Caruana	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Тип	Interactive supervised learning framework	Inductive transfer method	Learning paradigm
Основополагающий источник	Settles, B. (2009). Active learning literature survey. University of Wisconsin-Madison Computer Sciences Technical Report 1648.	Caruana, R. (1997). Multitask learning. Machine Learning, 28(1), 41–75.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Другие названия	Query Learning, Optimal Experimental Design (ML context), Pool-Based Active Learning, Aktif Öğrenme	MTL, Joint Learning, Shared Representation Learning, Çok Görevli Öğrenme	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Связанные	2	3	3
Сводка	Active learning is an iterative machine-learning paradigm in which a learning algorithm selectively queries an oracle — typically a human annotator — for labels on the most informative unlabeled examples. Formalized by Burr Settles in his seminal 2009 literature survey, active learning addresses the practical bottleneck of annotation cost by achieving high model accuracy with far fewer labeled examples than passive supervised learning requires.	Multitask Learning (MTL) is a machine learning paradigm in which a model is trained simultaneously on multiple related tasks, sharing representations across them to improve generalization. Introduced formally by Rich Caruana in 1997, MTL draws on the intuition that auxiliary tasks act as inductive bias, providing extra supervision signals that help the shared layers learn richer, more robust feature representations than single-task training would yield.	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.