Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Samoučící se Naive Bayes× | Samoučící se učení× | |
|---|---|---|
| Obor | Strojové učení | Strojové učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2000 | 2018–2020 |
| Tvůrce≠ | Nigam, K.; McCallum, A. K.; Thrun, S.; Mitchell, T. | LeCun, Y. and community (formalized ~2018–2020) |
| Typ≠ | Self-supervised generative classifier | Representation learning paradigm |
| Původní zdroj≠ | Nigam, K., McCallum, A. K., Thrun, S., & Mitchell, T. (2000). Text classification from labeled and unlabeled documents using EM. Machine Learning, 39(2-3), 103–134. DOI ↗ | 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 ↗ |
| Další názvy | Self-training Naive Bayes, EM Naive Bayes, Expectation-Maximization Naive Bayes, Pseudo-label Naive Bayes | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning |
| Příbuzné≠ | 5 | 3 |
| Shrnutí≠ | Self-supervised Naive Bayes extends the classic Naive Bayes classifier to exploit large pools of unlabeled data by iteratively assigning soft pseudo-labels through an Expectation-Maximization loop. Originally demonstrated for text classification by Nigam et al. (2000), the approach can substantially improve accuracy when labeled examples are scarce but unlabeled data are plentiful. | 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. |
| ScholarGateDatová sada ↗ |
|
|