Instructor: Stanley Chan, Purdue University
Level: Introductory
Prerequisites: Undergraduate probablility

Benefits:
This course enables the attendee to:

• Understand what generative AI means and how it works.
• Describe the basic principles of a variational autoencoder.
• Understand how denoising diffusion models are derived.
• Connect score matching with stochastic differential equations.
• Discuss the limitations of diffusion models.

Course Description:
The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some shortcomings that were deemed difficult in the previous approaches. This course discusses the essential ideas underlying the diffusion models. The target audience of this tutorial includes graduate students and researchers who are interested in doing research on diffusion models or applying these models to solve other problems. Topics include:

• Denoising diffusion probabilistic models (DDPM)
• Denoising diffusion implicit models (DDIM)
• Score-matching Lagenvin Dynamics (SMLD)
• Stochastic differential equation (SDE)

Course material is based on https://arxiv.org/abs/2403.18103

Intended Audience: Researchers and students working on machine learning, AI, computer vision, and imaging, who want to apply generative AI to their problems.

Stanley Chan is the Elmore Associate Professor of electrical and computer engineering at Purdue University. He received his PhD in electrical engineering and MA in mathematics from UC San Diego, and his BEng in electrical engineering from the University of Hong Kong. In 2012-2014, he was a postdoctoral research fellow at Harvard University. He is a senior member of IEEE. He is currently an Associate Editor of the IEEE Transactions on Computational Imaging, where he is recognized by the IEEE Signal Processing Society as an outstanding editorial board member. In IEEE, he was an elected member of the technical committee on computational imaging. He has also served as an associate editor for OSA Optics Express.