PIRSA:23030113

Video URL

https://pirsa.org/23030113

Diffusion Generative Models and potential applications in physics

Neklyudov, K. (2023). Diffusion Generative Models and potential applications in physics. Perimeter Institute for Theoretical Physics. https://pirsa.org/23030113

Neklyudov, Kirill. Diffusion Generative Models and potential applications in physics. Perimeter Institute for Theoretical Physics, Mar. 24, 2023, https://pirsa.org/23030113 

          @misc{ scivideos_PIRSA:23030113,
            doi = {10.48660/23030113},
            url = {https://pirsa.org/23030113},
            author = {Neklyudov, Kirill},
            keywords = {Other Physics},
            language = {en},
            title = {Diffusion Generative Models and potential applications in physics},
            publisher = {Perimeter Institute for Theoretical Physics},
            year = {2023},
            month = {mar},
            note = {PIRSA:23030113 see, \url{https://scivideos.org/pirsa/23030113}}
          }

Kirill Neklyudov Vector Institute for Artificial Intelligence

Talk numberPIRSA:23030113
DOI10.48660/23030113
Source RepositoryPIRSA
Collection
Talk Type Scientific Series
Subject

Abstract

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