Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Bayesovské učení z mála příkladů× | Učení s malým počtem příkladů× | |
|---|---|---|
| Obor | Strojové učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2018-2019 | 2011–2017 |
| Tvůrce≠ | Gordon et al.; Finn, Xu & Levine | Lake, B. M.; Vinyals, O.; Finn, C. et al. |
| Typ≠ | Probabilistic meta-learning | Meta-learning / low-data learning paradigm |
| Původní zdroj≠ | Gordon, J., Bronskill, J., Bauer, M., Nowozin, S. & Turner, R. E. (2019). Meta-Learning Probabilistic Inference for Prediction. International Conference on Learning Representations (ICLR 2019). 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 ↗ |
| Další názvy | Bayesian meta-learning, probabilistic few-shot learning, amortized Bayesian few-shot learning, Bayesian FSL | FSL, low-shot learning, k-shot learning, meta-learning for few examples |
| Příbuzné≠ | 5 | 4 |
| Shrnutí≠ | Bayesian few-shot learning combines Bayesian inference with meta-learning to enable a model to generalize from as few as one to five labeled examples per class. By treating task-specific parameters as random variables and learning an informative prior across many training tasks, the method produces calibrated uncertainty estimates alongside predictions — a key advantage over deterministic few-shot learners. | 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. |
| ScholarGateDatová sada ↗ |
|
|