Zapis dokaza metode
Semi-supervised GAN
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.
Izvorni zapis
Citati kopirani doslovno iz izvornog zapisa metode. Ne impliciraju nikakvu provjeru na razini tvrdnje.
Semi-supervised Generative Adversarial Network
Taksonomski zapis metode · ml-model / deep-learning
- 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. · URL
- Odena, A. (2016). Semi-Supervised Learning with Generative Adversarial Networks. ICML Workshop on Generative Adversarial Networks. · URL
Uređene tvrdnje
Tvrdnje pohranjene u knjigu dokaza, svaka s vlastitom procjenom.
Nema uređenih tvrdnji
Ovaj prikaz ne izmišlja procjenu tvrdnje kada knjiga dokaza nema nijednu.
Povezane metode
Generirano iz grafa metode i prikazano kao strojno predložene relacije — ne implicira se nikakva tvrdnja dokaza.