-
principled new models and methods, for modern machine learning problems. Machine learning recently has been largely advanced by differential equation-based frameworks, such as generative diffusion models
-
application! We are looking for a PhD student for sustainable and resource-efficient machine learning. Your work assignments Machine learning has recently advanced through scaling model sizes, training budgets
-
, data-driven control in high dimensions has penetrated many new application areas. Examples include control of autonomous vehicles based on video data, simulation-based prediction of turbulent flows and
-
work assignments A wide variety of physical phenomena like radio transmission, ultrasound, acoustics, or tsunami modelling involve the solution of partial differential equations (PDEs) that model wave
-
scaling model sizes, training budgets, and datasets; often at substantial computational and environmental costs. This PhD project targets sustainable and resource-efficient machine learning with a focus on
-
. Computational tools for simulating such processes - both traditional based e.g. on computational fluid dynamics and more recent based on AI/machine learning - constitute fundamental scientific domains that act as