השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| מודל דיפוזיה ניתן להסבר× | מפענח אוטומטי וריאציוני ניתן להסבר× | |
|---|---|---|
| תחום | למידה עמוקה | למידה עמוקה |
| משפחה | Machine learning | Machine learning |
| שנת המקור≠ | 2020–2022 | 2013–2017 |
| הוגה השיטה≠ | Ho, J., Jain, A., & Abbeel, P. (DDPM, 2020); XAI augmentation by subsequent researchers | Kingma, D. P. & Welling, M. (VAE); Higgins et al. (beta-VAE for disentanglement) |
| סוג≠ | Generative model with post-hoc or intrinsic explainability | Generative model with interpretable latent space |
| מקור מכונן≠ | Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems, 33, 6840–6851. link ↗ | Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR 2014). link ↗ |
| כינויים | XAI-DDPM, interpretable diffusion model, transparent diffusion model, explainable DDPM | XVAE, Interpretable VAE, Disentangled Variational Autoencoder, Explainable Generative Model |
| קשורות≠ | 6 | 4 |
| תקציר≠ | An Explainable Diffusion Model couples a denoising diffusion probabilistic model with post-hoc or intrinsic explainability techniques — such as SHAP, gradient-based saliency, attention analysis, or concept-based probing — so that each generative or predictive decision can be audited and justified rather than treated as a black box. | An Explainable Variational Autoencoder (XVAE) extends the standard VAE framework with techniques that make its latent space interpretable: disentangling latent dimensions so each corresponds to a human-understandable factor, or post-hoc attribution methods (SHAP, integrated gradients) that trace reconstructions back to input features. It retains the VAE's generative power while adding transparency required in scientific and high-stakes applications. |
| ScholarGateמערך נתונים ↗ |
|
|