Zurück

ARI Guest Talk on October 29, 2025, with Ole Christensen and Emily J. King

Join us for our guest talks with Professors Ole Christensen (DTU) and Emily J. King (Colorado State University). The afternoon features two short lectures that connect mathematical theory to real-world applications — from redundancy in signal representation to interpretability and reliability in AI.

Mittwoch 29.10.2025 01:10 Uhr
A scientist writes complex mathematical formulas and diagrams on a transparent surface, illustrating abstract problem-solving and analysis.
© Adobe Stock

Program
13:30–13:40 Introduction by Ole Christensen 
13:40–13:50 Introduction by Emily J. King 
14:00–14:30 Talk by Ole Christensen
14:45–15:15 Talk by Emily J. King

Talk 1: Redundancy

Speaker: Prof. Ole Christensen

Redundancy plays a role in the life of everybody. We repeat sentences (sometimes with a slight change of the wording) in order to make sure that a message is received, we double-check that the door is locked and the oven switched off, and so on.  The principle of redundancy is also incorporated in mathematical methods for signal transmission.  Such methods are often based on so-called frames, which are basic building blocks that can be used to represent arbitrary elements in the underlying (Hilbert) space.  The talk will focus on a class of frames,  for which surprisingly sparse subfamilies keep the frame property, due to a very particular "distribution" of the redundancy.

Ole Christensen is a Professor at the Department of Applied Mathematics and Computer Science at the Technical University of Denmark (DTU).
View profile


Talk 2: Interpretable, Explainable, and Adversarial AI: Data Science Buzzwords and You

Speaker: Prof. Emily J. King

Many state-of-the-art methods in machine learning are black boxes which do not allow humans to understand how decisions are made. In a number of applications, like medicine and atmospheric science, researchers do not trust such black boxes. Explainable AI can be thought of as attempts to open the black box of neural networks, while interpretable AI focuses on creating clear boxes. Adversarial attacks are small perturbations of data that cause a neural network to misclassify the data or act in other undesirable ways. Such attacks are potentially very dangerous when applied to technology like self-driving cars. The goal of this talk is to introduce mathematicians to problems they can attack using their favorite mathematical tools.  The mathematical structure of transformers, the powerhouse behind large language models like ChatGPT, will also be explained.

Emily J. King is a Professor at Colorado State University.
View profile

Informationen

 

Date:
Wednesday, October 29, 2025, 13:30

Venue:
Otto Wagner PSK Building
Meeting Room 1 | Third Floor
Georg Coch-Platz 2
1010 Vienna

Organizer:
Acoustics Research Institute of the OeAW
Tel.: +43 1 51581 2520