Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| Aprenentatge autosupervisat× | Aprenentatge amb pocs exemples× | |
|---|---|---|
| Camp | Aprenentatge automàtic | Aprenentatge automàtic |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 2018–2020 | 2011–2017 |
| Autor original≠ | LeCun, Y. and community (formalized ~2018–2020) | Lake, B. M.; Vinyals, O.; Finn, C. et al. |
| Tipus≠ | Representation learning paradigm | Meta-learning / low-data learning paradigm |
| Font seminal≠ | 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 ↗ | Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗ |
| Àlies | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning | FSL, low-shot learning, k-shot learning, meta-learning for few examples |
| Relacionats≠ | 3 | 4 |
| Resum≠ | 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. | Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited. |
| ScholarGateConjunt de dades ↗ |
|
|