Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Beijesiskā daļēji uzraudzītā apguve× | Mācīšanās ar maziem paraugu skaitu× | |
|---|---|---|
| Nozare | Mašīnmācīšanās | Mašīnmācīšanās |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2003–2006 | 2011–2017 |
| Autors≠ | Chapelle, Scholkopf & Zien; Zhu, Ghahramani & Lafferty | Lake, B. M.; Vinyals, O.; Finn, C. et al. |
| Tips≠ | Probabilistic semi-supervised framework | Meta-learning / low-data learning paradigm |
| Pirmavots≠ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.). (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 | 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 ↗ |
| Citi nosaukumi | Bayesian SSL, probabilistic semi-supervised learning, generative semi-supervised model, Bayesian transductive learning | FSL, low-shot learning, k-shot learning, meta-learning for few examples |
| Saistītās≠ | 6 | 4 |
| Kopsavilkums≠ | Bayesian semi-supervised learning is a probabilistic framework that uses both a small labeled dataset and a larger pool of unlabeled observations to infer model parameters and make predictions. By treating missing labels as latent variables and placing priors over parameters, it naturally quantifies uncertainty while leveraging unlabeled data to improve generalization. | 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. |
| ScholarGateDatu kopa ↗ |
|
|