Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Mācīšanās ar maziem paraugu skaitu× | Pašuzraudzības apmācība× | |
|---|---|---|
| Nozare | Mašīnmācīšanās | Mašīnmācīšanās |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2011–2017 | 2018–2020 |
| Autors≠ | Lake, B. M.; Vinyals, O.; Finn, C. et al. | LeCun, Y. and community (formalized ~2018–2020) |
| Tips≠ | Meta-learning / low-data learning paradigm | Representation learning paradigm |
| Pirmavots≠ | 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 ↗ | 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 ↗ |
| Citi nosaukumi | FSL, low-shot learning, k-shot learning, meta-learning for few examples | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| Saistītās≠ | 4 | 3 |
| Kopsavilkums≠ | 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. | 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. |
| ScholarGateDatu kopa ↗ |
|
|