Apr 2022
Abstract:
Realistic image generation has benefited from recent groundbreaking advances in the ML community. At the core of generative models lies the capability to sample high-dimensional distributions with relatively small support and a priori unknown shape. In many scientific applications, this capability is a limiting factor that has led to modeling choices that circumvent the sampling problem. In this talk, it is demonstrated how generative models can tackle outstanding scientific challenges by leveraging their ability to sample high-dimensional distributions, or directly estimate them. While generative models are typically understood as data augmentation tools, their ability to handle high-dimensional distributions makes them also suited for data reduction.
The sampling capabilities of generative models are illustrated for three scientific problems: atmospheric state inference, rare event probability estimation, and turbulent combustion modeling.
Bio:
Malik Hassanaly graduated with a PhD in Aerospace Engineering from the University of Michigan in 2019, an MSE from Ecole Centrale de Lille in 2015 and an MSE from University of Texas at Austin in 2014. He is currently working at the National Renewable Energy Laboratory as a post-doctoral researcher. His research interest includes extreme events in high-dimensional systems, computational modeling for fossil and renewable energy applications, and scientific machine-learning.
Registration link to join the seminar:
https://kaust.zoom.us/webinar/register/WN_mxGB1dg5QF6rOlreJF90aA