Diffusion-based generative models such as DALL·E 2 have achieved exceptional image generation quality. Unlike other generative models based on explicit representations of probability distributions (e.g., autoregressive) or implicit sampling procedures (e.g., GANs), diffusion models learn directly the vector field of gradients of the data distribution (scores). This framework allows flexible architectures, requires no sampling during training or the use of adversarial training methods. These score-based generative models enable exact likelihood evaluation, achieve state-of-the-art sample quality, and can be used to improve performance in a variety of inverse problems, including medical imaging.
Stefano Ermon, Assistant Professor @ Stanford University
Stefano Ermon is an Associate Professor of Computer Science in the CS Department at Stanford University, where he is affiliated with the Artificial Intelligence Laboratory, and a fellow of the Woods Institute for the Environment. His research is centered on techniques for probabilistic modeling of data and is motivated by applications in the emerging field of computational sustainability. He has won several awards, including Best Paper Awards (ICLR, AAAI, UAI and CP), a NSF Career Award, ONR and AFOSR Young Investigator Awards, Microsoft Research Fellowship, Sloan Fellowship, and the IJCAI Computers and Thought Award. Stefano earned his Ph.D. in Computer Science at Cornell University in 2015.
Course curriculum
-
1
Denoising Diffusion-based Generative Modeling
-
Denoising Diffusion-based Generative Modeling
-