Сравнение методов
Просматривайте выбранные методы рядом; строки с различиями подсвечены.
| Обучение метрике с частичным привлечением учителя× | Перенос обучения× | |
|---|---|---|
| Область | Машинное обучение | Машинное обучение |
| Семейство | Machine learning | Machine learning |
| Год появления≠ | 2007–2008 | 2010 (formalized); 1990s (early roots) |
| Автор метода≠ | Yeung, D.-Y. & Chang, H.; Davis, J. V. & Dhillon, I. S. | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) |
| Тип≠ | Hybrid supervised/unsupervised distance learning | Learning paradigm |
| Основополагающий источник≠ | Yeung, D.-Y., & Chang, H. (2007). A kernel approach for semi-supervised metric learning. IEEE Transactions on Neural Networks, 18(1), 141–149. DOI ↗ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| Другие названия | SSML, semi-supervised distance learning, constrained metric learning, weakly supervised metric learning | TL, domain adaptation, fine-tuning, pre-trained model adaptation |
| Связанные≠ | 5 | 3 |
| Сводка≠ | Semi-supervised metric learning learns a task-adapted distance function by combining a small set of labeled pairwise constraints — must-link and cannot-link pairs — with the geometric structure of a much larger pool of unlabeled data. The result is a Mahalanobis-style or kernel-based distance that reflects both supervision and data topology, improving downstream tasks such as nearest-neighbor classification and clustering. | 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. |
| ScholarGateНабор данных ↗ |
|
|