StochasticAI – Integrating Stochastic Modeling with AI
Mentored by Sayan Mukerhjee & Ivo Sbalzarini
at TU Dresden or Leipzig University (please indicate preference)
We will consider the integration of classical stochastic modeling (including numerical methods, Bayesian statistics, and inverse problems approaches) with modern AI methodology. The idea is to build more efficient, reliable, and interpretable algorithms that also quantify uncertainty. We will consider variational formulations of various learning problems as a starting point to solve challenging inverse problems in complex settings as well as solving challenging sampling problems central to many inference and learning applications. We will also use ideas from statistical physics and dynamical systems to develop algorithms.
Work Environment
You will have access to the machine-learning HPC resources of the ScaDS.AI Center for Scalable Data Analytics and AI Dresden/Leipzig, offering state-of-the-art CPU (Intel and IBM POWER 9) and GPU (Nvidia A100 and V100) resources, as well as high-performance computing and storage systems for computational experiments. You will also be working with the machine learning and AI people at the Center for Systems Biology Dresden (CSBD), a joint center between the Max Planck Society and TU Dresden, and the Interdisciplinary Center for Bioinformatics, a similar joint center between the Max Planck Society and Leipzig University.
Prerequisites
The candidate will need a solid background in mathematics (an emphasis on high-dimensional statistics, functional analysis or topology will be an advantage). Since the work will require extensive computational experimentation, proficiency in scientific programming and interest in data analysis are necessary.
Topics All Topics
Adaptive / Context Sensitive Data Provision in Mobile Applications
AI Controlled Wireless Mesh Networks for Medical Applications in Crisis Situations (AWESOME)
Artificial Intelligence in the Context of Biomedical Signals
External Systems Biology Knowledge Integration in Large Language Models
Features of Fitness Landscapes
From protein structure prediction to explainable AI in Oncology
GeoSOP: Geometry for surgical outcome prediction
Natural Neural networks inspire Artificial Neural Networks in Therapeutic Design
Reinforcement Learning for Mechanical Ventilation
RelAiMed: Explainable AI for reliable computer assisted surgery
StochasticAI – Integrating Stochastic Modeling with AI
SuperTouch - Data-driven tactile sensing for robot-assisted cancer surgery
Teaching artificial intelligence conformational dynamics of proteins
The Use of AI by the Civil Service in Light of the Principles of Democracy and the Rule of Law