Seminars

Mike Gordon’s Higher-Order Logic (HOL) is one of the most important logical foundations for interactive theorem proving. The standard semantics of HOL, due to Andrew Pitts, employs a downward closed universe of sets, and interprets HOL’s Hilbert choice operator via a
global choice function on the universe.

Large language models (LLMs) are helping millions of users to learn and write about a diversity of issues. In doing so, LLMs may expose users to new ideas and perspectives, or reinforce existing knowledge and user opinions.

Abstract not available

For centuries, unraveling the mysteries of nature through the lens of physics has captivated countless scientists.

Abstract not available

Many cloud and edge AI services today perform machine learning inference in real time on end user requests. Over time, however, models could degrade in accuracy due to data and concept drifts, and full retraining can be infeasible because of limited training data, long training delay, and prohibitive computational overhead.

The seminar will be an interdisciplinary journey between applications of Artificial Intelligence (AI) Computer Vision based methods to the field of Forensics and Biomedical Imaging.

Abstract not available

Equivariance can enhance the data efficiency of machine learning models by incorporating prior knowledge about a problem.
Thanks to their flexibility and generality, steerable CNNs are a popular design choice for equivariant networks.

Abstract not available