ScholarGate
المساعد

قارن الطرق

راجع الطرق التي اخترتها جنبًا إلى جنب؛ الصفوف المختلفة مميَّزة.

شبكة الخصومة التوليدية شبه الخاضعة للإشراف×شبكة الخصومة التوليدية×
المجالالتعلم العميقالتعلم العميق
العائلةMachine learningMachine learning
سنة النشأة20162014
صاحب الطريقةOdena, A.; Salimans, T. et al.Goodfellow, I. et al.
النوعSemi-supervised generative modelGenerative deep learning (adversarial two-network game)
المصدر التأسيسيSalimans, 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 ↗
الأسماء البديلةSGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learningÜretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
ذات صلة54
الملخصSemi-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.
ScholarGateمجموعة البيانات
  1. v1
  2. 2 المصادر
  3. PUBLISHED
  1. v1
  2. 2 المصادر
  3. PUBLISHED

انتقل إلى البحث تنزيل الشرائح

ScholarGateقارن الطرق: Semi-supervised GAN · Generative Adversarial Network. استُرجع بتاريخ 2026-06-17 من https://scholargate.app/ar/compare