Navigation auf uzh.ch
Navigation auf uzh.ch
Speaker:
Prof. Dr. Michael Cochez, VU Vrije University Amsterdam, The Netherlands
Date: Thursday, 21 November 2024, 17:15
Location: room BIN 2.A.01 at the Department of Informatics (IfI), Binzmühlestrasse 14, 8050 Zürich (information here)
Details about the format of the talk shall be checked always just ahead of a certain presentation date: (information here)
Recent advances in machine learning, especially with language models, have transformed many fields, dramatically raising expectations for artificial intelligence systems. Yet, these advances have also exposed a critical weakness: a lack of reliability. In contrast, traditional AI methods offer more dependable but less flexible solutions, often limiting their broad applicability.
In this talk, we will explore the intersection of these approaches. I'll introduce how graph-based knowledge can be used by machine learning systems, retaining both flexibility and robustness. I'll also share our latest research on inductive representation learning and neural graph reasoning, highlighting how these techniques address key challenges in AI today.
Dr. Michael Cochez is an assistant professor in the Learning and Reasoning group at the Vrije Universiteit Amsterdam and manager of the Discovery Lab (an ICAI lab in collaboration with Elsevier and the University of Amsterdam). He works on bridging the gap between knowledge graphs and machine learning. His research interests include embedding of knowledge graphs for downstream machine learning tasks, dealing with missing information in graphs (link prediction, approximate graph query answering) and applications such as question answering and recommendations.
