Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| GAN semi-supervizat× | Învățare semi-supervizată× | |
|---|---|---|
| Domeniu≠ | Învățare profundă | Învățare automată |
| Familie | Machine learning | Machine learning |
| Anul apariției≠ | 2016 | 1970s–2006 (formalized) |
| Autorul original≠ | Odena, A.; Salimans, T. et al. | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| Tip≠ | Semi-supervised generative model | Learning paradigm |
| Sursa seminală≠ | Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| Denumiri alternative | SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| Înrudite | 5 | 5 |
| Rezumat≠ | Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few 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. |
| ScholarGateSet de date ↗ |
|
|