World Logic Day Lecture: Joao Marques-Silva
Trustable Explainable AI -- A Redemption by Logic
| DATE: | Tuesday, January 14, 2025 |
| TIME: | 17:00 |
| VENUE: | zoom and youtube |
On 14 January 2025, we invite you to celebrate the international World Logic Day virtually with the Vienna Center for Logic and Algorithms (VCLA) at TU Wien and the Logic community from the city of Kurt Gödel, Ludwig Wittgenstein, and the Vienna Circle.
UNESCO proclaimed World Logic Day in 2019 in association with the International Council for Philosophy and Human Sciences (CIPSH) to enhance public understanding of logic and its implications for science, technology and innovation. “In the twenty-first century – indeed, now more than ever – the discipline of logic is a particularly timely one, utterly vital to our societies and economies. Computer science and information and communications technology, for example, are rooted in logical and algorithmic reasoning.” — Audrey Azoulay, Director General of UNESCO
We are happy to announce that the 2025 virtual Vienna World Logic Day Lecture will be held by Joao Marques-Silva (ICREA and University of Lleida).
Click here for free registration via Zoom!
Topic: Trustable Explainable AI — A Redemption by Logic
Abstract
Explainable artificial intelligence (XAI) is a mainstay of trustworthy AI. Recent years have witnessed massive efforts towards delivering some sort of XAI solutions. Most of these efforts are based on non-symbolic methods, and invariably will produce erroneous results. As a result, even if the predictions of a machine learning model could be trusted, the lack of reliable explanations will also make those predictions unworthy of trust. This talk provides a brief glimpse of the emerging field of logic-based explainable AI, a rigorous alternative to the still widely-used but extremely problematic non-symbolic methods.
About the speaker
Joao Marques-Silva is a Research Professor at ICREA, and affiliated with the University of Lleida. Before joining ICREA, he was Research Director (Directeur de Recherche) at CNRS (Centre National de la Recherche Scientifique), affiliated with IRIT (Institut de Recherche en Informatique de Toulouse), Toulouse, France and principal researcher of ANITI’s Chair on Deep Learner Explanation and Verification (DeepLEVER) (the team’s publications are available here). In addition, and before joining IRIT/CNRS & ANITI, he was affiliated as Professor of Computer Science with University College Dublin (IE), the University of Southampton (UK), and the University of Lisbon (PT). He received the PhD from the University of Michigan, Ann Arbor (USA). His research interests include automated reasoning, artificial intelligence and machine learning.
