Join us for an exciting double lecture event at LMU Munich, featuring Prof. Dr. Franca Hoffmann and Prof. Dr. Holger Hoos, two renowned experts in artificial intelligence and mathematics who will present cutting-edge research on strategic dynamics and neural network robustness.

Lecture 1: Dynamics of Strategic Agents and Algorithms as PDEs 

Prof. Dr. Franca Hoffmann will explore how algorithms and strategic agents influence each other’s behavior, creating complex dynamics that can be difficult to predict. Using ideas from game theory, she introduces a mathematical framework to model these interactions, represented by partial differential equations (PDEs) that describe how players adjust their strategies over time. The framework helps explain long-term outcomes and models real-world scenarios more effectively than simpler methods, showing how such dynamics can be captured and understood.

Lecture 2: Learning, Reasoning, and Optimization: Adversarial Robustness of Neural Networks 

Prof. Dr. Holger Hoos will provide an introduction to neural network robustness and explain how work in this area effectively combines AI methods from machine learning, optimization, and automated reasoning. He will explain the concept of robustness verification and introduce local robustness distributions, which afford a rigorous and nuanced assessment of neural network robustness against input perturbations. He will give examples from image and audio classification and briefly discuss connections to questions of bias and fairness, as well as the way in which this line of work relates to the broader effort of his group towards safe, dependable, and sustainable AI.