Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| GAN semi-supervisionato× | Rete Generativa Avversaria× | |
|---|---|---|
| Campo | Apprendimento profondo | Apprendimento profondo |
| Famiglia | Machine learning | Machine learning |
| Anno di origine≠ | 2016 | 2014 |
| Ideatore≠ | Odena, A.; Salimans, T. et al. | Goodfellow, I. et al. |
| Tipo≠ | Semi-supervised generative model | Generative deep learning (adversarial two-network game) |
| Fonte seminale≠ | 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 ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ |
| Alias | SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network |
| Correlati≠ | 5 | 4 |
| Sintesi≠ | 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. | A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation. |
| ScholarGateInsieme di dati ↗ |
|
|