Porovnať metódy
Prezrite si vybrané metódy vedľa seba; riadky, ktoré sa líšia, sú zvýraznené.
| Samoučenie× | Polosupervizované učenie× | |
|---|---|---|
| Odbor | Strojové učenie | Strojové učenie |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2018–2020 | 1970s–2006 (formalized) |
| Tvorca≠ | LeCun, Y. and community (formalized ~2018–2020) | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| Typ≠ | Representation learning paradigm | Learning paradigm |
| Pôvodný zdroj≠ | 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 ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| Ďalšie názvy | SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| Príbuzné≠ | 3 | 5 |
| Zhrnutie≠ | 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. | Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained. |
| ScholarGateDátová sada ↗ |
|
|