Seminar Tübingen-Nancy Philosophical Aspects of Computer Sciences – Ethics, Norms & Responsibility Organisation : Maël Pégny, Reinhard Kahle, Thomas Piecha, Anna Zielinska, Cyrille Imbert Archives Henri Poincaré - Philosophie et Recherches sur les Sciences et les Technologies / Université de Lorraine, France Universität Tübingen, Germany
Carmela Troncoso École polytechnique fédérale de Lausanne (EPFL), SPRING Lab Mismatching concerns and definitions in current trends in machine learning Lundi 21 février 2022, à 17h00, en ligne. L'exposé et la discussion auront lieu en anglais. 21 February 2022, Monday 17:00 (CET/time of Paris) Please register by clicking here (for this and for the future meetings of the seminar) https://forms.gle/papVbAjPoyoGEqTH9 Both the lecture and the discussion will be in English. https://www.facebook.com/events/333894508653632 Abstract In this talk we will revisit current approaches to fairness and privacy in machine learning, and take a critical look at the concerns they address. We will show that concerns are modeled in a narrow way, and therefore the proposed solutions fall short to provide the protections that are promised in the literature. We will look at three examples and discuss the implications of the mismatch on how these systems may affect society if deployed. **** Our first season 2021-2022 15 November 2021 Maël Pégny Mathematizing fairness? On statistical metrics of algorithmic fairness 21 February 2022 Carmela Troncoso Mismatching concerns and definitions in current trends in machine learning 21 March 2022 Marija Slavkovik Digital Voodoo Dolls 11 April 2022 Karoline Reinhardt Dimensions of trust in AI Ethics For the recording of the seminar, please check here: https://www.youtube.com/playlist?list=PL_7w_H-zjjuEqhh4gLTWg5MbmbTfGmXIU Initial context of the event: Project Open Language and Knowledge for citizens (OLKi) [ http://lue.univ-lorraine.fr/fr/open-language-and-knowledge-citizens-olki] is involved in the design of new machine learning algorithms dedicated to knowledge extraction from language data, with a focus on transparency, explainability of algorithms, and open and privacy-friendly science. -- https://www.vidal-rosset.net/mailing_list_educasupphilo.html
