השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| אימון יריבי (Adversarial Training)× | רשת יריבות יוצרת (Generative Adversarial Network)× | |
|---|---|---|
| תחום | למידה עמוקה | למידה עמוקה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2018 | 2014 |
| הוגה השיטה≠ | Aleksander Madry et al. | Goodfellow, I. et al. |
| סוג≠ | Robust optimization training procedure | Generative deep learning (adversarial two-network game) |
| מקור מכונן≠ | Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. International Conference on Learning Representations (ICLR). link ↗ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ |
| כינויים | Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network |
| קשורות≠ | 3 | 4 |
| תקציר≠ | Adversarial Training is a robust optimization procedure for deep neural networks in which the model is trained not on clean data alone but on worst-case perturbed inputs crafted during training. Formalized by Madry et al. (2018) as a min-max saddle-point problem, the method uses Projected Gradient Descent (PGD) to generate strong adversarial examples within a bounded Lp perturbation set before each gradient update, forcing the network to learn decision boundaries that are stable under such perturbations. | 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. |
| ScholarGateמערך נתונים ↗ |
|
|