Sponsored by
 
Events
News
 
[ Events ]
Seminars and Talks Conferences, Workshops and Special Events Courses and Lecture Series Taiwan Math. School
 

Activity Search
Sort out
Field
 
Year
Seminars  
 
NCTS Probability Seminar
 
14:00 - 15:00, May 14, 2025 (Wednesday)
Room 505, Cosmology Building, National Taiwan University + Cisco WebEx, Physical+Online Seminar
(實體+線上演講 台灣大學次震宇宙館505研討室+ Cisco WebEx)
Mathematical Formulation of Diffusion Models in Machine Learning
Shang-Yuan Shiu (National Central University)

Abstract
This talk offers a mathematical introduction to diffusion models in generative AI, based on their original formulations as presented in references [1] and [2], without introducing new insights. We will begin by discussing diffusion processes. Within the context of diffusion models, we will illustrate both the forward and reverse diffusion processes, highlighting their roles within the generative AI framework. The emphasis will be on the mathematical structure rather than intuitive explanations or theoretical justifications.
 
References
[1] Ho, J., Jain, A., and Abbeel, P. (2020). Denoising Diffusion Probabilistic Models.
[2] Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., and Surya Ganguli. (2015). Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In International Conference on Machine Learning, 2256–2265
 
Meeting number (access code): 2514 242 9124
Meeting password: HRkmwDDN822
 
Organizers: Jhih-Huang Li (NTU), Wai Kit Lam (NTU)


 

back to list  
(C) 2021 National Center for Theoretical Sciences