Jürgen Hesser
Professor for Data Analysis and Modeling in Medicine
Faculty of Medicine Mannheim
Co-opted: Department of Physics and Astronomy
Heidelberg University
Introduction
My research:
Inverse Problems with a focus on model-based Machine Learning
My expertise is:
Scientific Computing with focus on Inverse Problems
Machine Learning methods development
Causal modeling
A problem I’m grappling with:
Overcoming hard problems of applying machine learning in scientific computing such as using PINNs for stiff differential equations
I’ve got my eyes on:
Mathematical foundations on ML
I want to know more about:
Incorporating combining the physics with ML
Projects
Physics Model-Based AI for Rare Events
Develop a novel strategy to perform reliable extrapolation with machine learning (ML) by space-unwrapping; efficiently handle extreme value modelling via machine learning using model-based strategies like exponentially tiled estimators; solve stochastic partial differential equations via physics informed neural networks for transport equations.
Denoising diffusion probabilistic models
Develop novel methods of inverse problem solutions based on denoising diffusion probabilistic models; investigate new approaches to uncertainty estimation based on stochasticity of denoising diffusion models; introduce new techniques of conditional generation based on concatenation, cross-attention and bias.
New Generative Models for Parton Distributions
The goal of the project is to switch from the current situation, in which a hyperoptimized machine learning model leads to results whose accuracy is tested a posteriori, to interpretable models in which the relation between experimental, theoretical and modeling uncertainty and the uncertainties in the final outcome can be traced using explainable AI tools.
