השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| למידה פעילה עם למידה מונחית-עצמית× | למידה בפיקוח עצמי× | |
|---|---|---|
| תחום | למידת מכונה | למידת מכונה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2020-2022 | 2018–2020 |
| הוגה השיטה≠ | Multiple authors (active learning + SSL integration, 2020s) | LeCun, Y. and community (formalized ~2018–2020) |
| סוג≠ | Hybrid learning paradigm | Representation learning paradigm |
| מקור מכונן≠ | Bengar, J. Z., van de Weijer, J., Fuentes, L. L., & Raducanu, B. (2022). Class-Balanced Active Learning for Image Classification. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 3082–3091. link ↗ | 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 ↗ |
| כינויים | AL-SSL, active self-supervised learning, self-supervised active learning, query-based self-supervised learning | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| קשורות≠ | 6 | 3 |
| תקציר≠ | Active learning combined with self-supervised learning leverages unlabeled data through self-supervised pre-training to build rich representations, then uses an active query strategy to select the most informative examples for human annotation, maximizing model performance under a tight labeling budget. This hybrid approach is especially powerful when labeled data is scarce but large unlabeled pools exist. | 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. |
| ScholarGateמערך נתונים ↗ |
|
|