Generative AI for image applications
(July 3, 3:30 PM - 4:30 PM)
"Expert in the fields of statistics and artificial intelligence, Éric Moulines has been a professor at the CMAP at the École Polytechnique since 2015. A former teacher-researcher at Télécom Paris, he is also a member of the Académie des Sciences. His research topics research topics include Monte Carlo methods, statistical learning, Bayesian Bayesian networks, probabilistic models, optimization algorithms and signal processing. signal processing. His in-depth knowledge of these subjects led him to initiate in 2020 the ""AI & Positive Maintenance"" Chair, after having implemented the ""Next-Gen RetAIl"", ""Data Science Institute"" and ""Data Science & Industrial Processes"" since 2017. He is Scientific co-Director of Hi! PARIS Center since 2020."
The main goal of this talk is to give the participants a comprehensive overview of the different methods of generative modeling, with special attention to their application in image generation. The talk will cover different techniques and models from this field.
We will look first at state-of-the-art image models such as Variational AutoEncoders (VAEs), Generative Adversarial Networks (GANs), and Normalizing Flows (NFs). These state-of-the-art models have revolutionized the field and have been instrumental in generating realistic images. In addition, we will explore the applications of these models in the context of conditional image generation so that participants understand how these techniques can be used in practical scenarios.
We will then focus to an emerging competitor in the generative modeling field, diffusion models or Score-Based Generative Models (SGMs). We will gain an in-depth understanding of the mathematical principles underlying these models, including the time-reversal of stochastic processes. We will also explore the connections between diffusion models and Regularized Optimal Transport and their applications in control theory.