Сравнение методов

	Метрическое обучение	Онлайн-обучение	Нейронная сеть «Сиамская»
Область	Машинное обучение	Машинное обучение	Глубокое обучение
Семейство	Machine learning	Machine learning	Machine learning
Год появления	2003 (foundational); refined 2009 (LMNN)	1958–2000s	1993
Автор метода	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.	Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors)	Jane Bromley & Yann LeCun et al.; popularized by Koch et al.
Тип	Representation learning / supervised distance optimization	Learning paradigm (sequential model update)	Deep metric-learning architecture
Основополагающий источник	Xing, E. P., Jordan, M. I., Russell, S., & Ng, A. Y. (2003). Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems (NIPS), 16, 505–512.	Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194.	Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., & Shah, R. (1993). Signature verification using a 'Siamese' time delay neural network. Advances in Neural Information Processing Systems, 6.
Другие названия	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance	incremental learning, sequential learning, streaming learning, online machine learning	twin network, Siamese neural network, contrastive metric network, Siyam ağı
Связанные	5	6	1
Сводка	Metric learning is a machine-learning framework that trains a distance or similarity function from data so that semantically similar examples end up close together in the learned space while dissimilar examples are pushed apart. Unlike fixed distances such as Euclidean, the learned metric adapts to the structure of the task, making downstream classifiers, clusterers, and retrieval systems significantly more accurate.	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.	A Siamese network is a deep architecture with two (or more) identical, weight-sharing branches that map inputs into an embedding space where similar inputs land close together and dissimilar ones far apart. Introduced by Bromley, LeCun, and colleagues in 1993 for signature verification and revived by Koch et al. (2015) for one-shot image recognition, it learns a similarity metric rather than fixed class labels, making it ideal for verification, matching, and few-shot tasks.