So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Transfer Learning× | Học tăng cường tự giám sát× | |
|---|---|---|
| Lĩnh vực | Học máy | Học máy |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2010 (formalized); 1990s (early roots) | 2018–2020 |
| Người khởi xướng≠ | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) | LeCun, Y. and community (formalized ~2018–2020) |
| Loại≠ | Learning paradigm | Representation learning paradigm |
| Công trình gốc≠ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ | LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/ link ↗ |
| Tên gọi khác | TL, domain adaptation, fine-tuning, pre-trained model adaptation | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| Liên quan | 3 | 3 |
| Tóm tắt≠ | 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. | Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples. |
| ScholarGateBộ dữ liệu ↗ |
|
|