Diffusion Generative Models and potential applications in physics
PIRSA ID:
23030113
Série :
Machine Learning Initiative
Event Type:
Seminar
Domaine(s) scientifique(s) :
Other
Date de fin :
Speaker(s):
- Kirill Neklyudov, Vector Institute for Artificial Intelligence
Generative modeling via diffusion processes is already a vast field of literature. In this introduction, I will give an entry point to this field by going over the main concepts and deriving the essential results of the area. Thus, by the end of the talk, we would have a minimal pipeline for implementing the generative model. Furthermore, I will outline several alternative ways for learning such models that the community has developed in recent years. These directions bring novel perspectives and new capabilities of generative modeling.
Zoom link: https://pitp.zoom.us/j/98786491081?pwd=U1cvZzBQT2VUZDl5Ykd0c1lqY29aZz09