Dear all, Dr. Francesco Leofante (invited by Prof. Dr. Matthias Thimm) will deliver the next Oberseminar (14th November,10:00, via Zoom): Title: Robustness issues in algorithmic recourse. Abstract: Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this talk we will begin by introducing the problem of (lack of) robustness, discuss its implications and present some recent solutions we developed to compute CEs with robustness guarantees. Bio: Francesco is an Imperial College Research Fellow affiliated with the Centre for Explainable Artificial Intelligence at Imperial College London. His research focuses on safe and explainable AI, with special emphasis on counterfactual explanations and their robustness. Since 2022, he leads the project “ConTrust: Robust Contrastive Explanations for Deep Neural Networks”, a four-year effort devoted to the formal study of robustness issues arising in XAI. More details about Francesco and his research can be found at https://fraleo.github.io/. **We cordially ask the attendees to turn on their cameras and turn off their microphones during the presentation. Zoom Room: https://eur05.safelinks.protection.outlook.com/?url=https%3A%2F%2Ffernuni-hagen.zoom.us%2Fj%2F62388524887%3Fpwd%3DWmJRRUpDZWZ4WlJoeFlGQTBESWplQT09&data=05%7C02%7Csteffi.bluemel%40fernuni-hagen.de%7C42fe776c1f324ba6b7aa08dc223844de%7Cc2bba033db424b299adb6ac379499ef7%7C1%7C0%7C638422872265614676%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=X%2F4UFs7fFH%2BIDLw7SsgOOqv3FUyNoCPE7k9B7YFDaGE%3D&reserved=0<https://fernuni-hagen.zoom.us/j/62388524887?pwd=WmJRRUpDZWZ4WlJoeFlGQTBESWplQT09> --- Current Scheduled Talks ---- * 14th November, Dr. Francesco Leofante (invited speaker) * 21st November, Ulrich Karkmann, BSc proposal * 28th November, Badran Raddaoui (invited speaker) * 05th December, Ralf Hager * 12th December, Dominik Lewin * 19th December, Joris Plettscher, BSc proposal If you do not wish to receive messages from this mailing list anymore, please let me know by simply responding „unsubscribe“ to this mail (steffi.bluemel@fernuni-hagen.de<mailto:steffi.bluemel@fernuni-hagen.de>). Best regards, Steffi Blümel - Sekretariat - ---------------------------------------------------- FernUniversität in Hagen Fakultät Mathematik und Informatik / Lehrgebiet Künstliche Intelligenz Universitätsstraße 1 58097 Hagen Fon: + 49 23 31 - 9 87 40 06 E-Mail: steffi.bluemel@fernuni-hagen.de<mailto:steffi.bluemel@fernuni-hagen.de>
Dear all, Prof. Dr. Badran Raddaoui (invited by Prof. Dr. Matthias Thimm) will deliver the next Oberseminar (28th November,10:00, via Zoom): Title: „Normative reasoning based on inconsistency measures“ Abstract: Conflicts are inherent to normative systems and can manifest in various logical forms. In this talk, I will present a novel approach to normative reasoning by quantifying the amount of conflicts within normative systems. We refine the idea from classical logic, according to which a formula is a consequence of a knowledge base if its negation renders the base inconsistent. Our approach evaluates whether a formula is a logical consequence based, for instance, on its negation's marginal contribution to the inconsistency of the knowledge base. To this end, I will propose various inconsistency measures and corresponding nonmonotonic and paraconsistent normative entailment relations. I will also provide a systematic analysis of these entailment relations by examining them against a number of logical properties. To illustrate our approach, we employ Input/Output logic, a renowned formalism in deontic logic, specifically designed for defeasible normative reasoning. **We cordially ask the attendees to turn on their cameras and turn off their microphones during the presentation. Zoom Room: https://eur05.safelinks.protection.outlook.com/?url=https%3A%2F%2Ffernuni-hagen.zoom.us%2Fj%2F62388524887%3Fpwd%3DWmJRRUpDZWZ4WlJoeFlGQTBESWplQT09&data=05%7C02%7Csteffi.bluemel%40fernuni-hagen.de%7C42fe776c1f324ba6b7aa08dc223844de%7Cc2bba033db424b299adb6ac379499ef7%7C1%7C0%7C638422872265614676%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=X%2F4UFs7fFH%2BIDLw7SsgOOqv3FUyNoCPE7k9B7YFDaGE%3D&reserved=0<https://fernuni-hagen.zoom.us/j/62388524887?pwd=WmJRRUpDZWZ4WlJoeFlGQTBESWplQT09> --- Current Scheduled Talks ---- * 28th November, Prof. Dr. Badran Raddaoui (invited speaker) * 05th December, Ralf Hager * 12th December, Dominik Lewin * 19th December, Joris Plettscher, BSc defense If you do not wish to receive messages from this mailing list anymore, please let me know by simply responding „unsubscribe“ to this mail (steffi.bluemel@fernuni-hagen.de<mailto:steffi.bluemel@fernuni-hagen.de>). Best regards, Steffi Blümel - Sekretariat - ---------------------------------------------------- FernUniversität in Hagen Fakultät Mathematik und Informatik / Lehrgebiet Künstliche Intelligenz Universitätsstraße 1 58097 Hagen Fon: + 49 23 31 - 9 87 40 06 E-Mail: steffi.bluemel@fernuni-hagen.de<mailto:steffi.bluemel@fernuni-hagen.de>
Teilnehmer (1)
-
Blümel, Steffi