השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| רשת יריבות יוצרת (Generative Adversarial Network)× | מודל דיפוזיה× | |
|---|---|---|
| תחום | למידה עמוקה | למידה עמוקה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2014 | 2020 |
| הוגה השיטה≠ | Goodfellow, I. et al. | Ho, J., Jain, A. & Abbeel, P. |
| סוג≠ | Generative deep learning (adversarial two-network game) | Generative deep learning (denoising diffusion) |
| מקור מכונן≠ | Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗ | Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS. link ↗ |
| כינויים≠ | Üretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network | Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM |
| קשורות | 4 | 4 |
| תקציר≠ | 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. | A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling. |
| ScholarGateמערך נתונים ↗ |
|
|