BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Paris BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260206T100253Z UID:01E75BCF-0A33-45A1-A7D7-CC6C04468EDB DTSTART;TZID=Europe/Paris:20260203T140000 DTEND;TZID=Europe/Paris:20260203T150000 DESCRIPTION:Title: A journey through Deep Neural Network Debiasing\n\nAbstr act:\nDeep neural networks frequently encode and propagate biases arising from data\, model design\, and deployment contexts\, posing significant ch allenges for reliable and lawful AI systems. This presentation surveys deb iasing techniques for deep neural networks\, situating them within the reg ulatory constraints introduced by the AI Act. We compare supervised and un supervised debiasing methods\, emphasizing their underlying assumptions\, optimization objectives\, and practical trade-offs. The talk then addresse s bias discovery and bias naming as foundational problems for systematic b ias mitigation. Finally\, we discuss emerging research directions\, includ ing privacy-aware debiasing\, fairness certification\, and machine unlearn ing\, highlighting open technical challenges and unresolved tensions betwe en fairness\, robustness\, and compliance.\n\nBio:\nEnzo Tartaglione is a Full Professor at Télécom Paris\, where he is responsible for the equipe Multimedia and he is a Hi!Paris associate member. He is also a Member of the ELLIS Society\, Senior IEEE Member\, Associate Editor of IEEE Transact ions on Neural Networks and Learning Systems\, Action Editor for Transacti ons of Machine Learning Research and of the EURASIP Journal on Image and V ideo Processing. He received the MS degree in Electronic Engineering at Po litecnico di Torino in 2015\, cum laude. The same year\, he also received a magna cum laude MS in electrical and computer engineering at University of Illinois at Chicago. In 2016 he was also awarded the MS in Electronics by Politecnico di Milano\, cum laude. In 2019 he obtained a PhD in Physics at Politecnico di Torino\, cum laude\, with the thesis "From Statistical Physics to Algorithms in Deep Neural Systems". His principal interests inc lude compression and responsible (frugal) AI\, privacy-aware learning\, da ta debiasing\, and regularization for deep learning.\n\nCo-sponsored by: F rank Wang\n\nVirtual: https://events.vtools.ieee.org/m/534567 LOCATION:Virtual: https://events.vtools.ieee.org/m/534567 ORGANIZER:Ambarish.natu@gmail.com SEQUENCE:4 SUMMARY:A journey through Deep Neural Network Debiasing URL;VALUE=URI:https://events.vtools.ieee.org/m/534567 X-ALT-DESC:Description: <br /><div><strong><span data-removefontsize="true" data-originalcomputedfontsize="16">Title:&nbsp\;</span><span data-removef ontsize="true" data-originalcomputedfontsize="16">A journey through Deep N eural Network Debiasing</span></strong></div>\n<p><br><strong data-removef ontsize="true" data-originalcomputedfontsize="16">Abstract:&nbsp\;</strong ></p>\n<div data-removefontsize="true" data-originalcomputedfontsize="16"> Deep neural networks frequently encode and propagate biases arising from d ata\, model design\, and deployment contexts\, posing significant challeng es for reliable and lawful AI systems. This presentation surveys debiasing techniques for deep neural networks\, situating them within the regulator y constraints introduced by the AI Act. We compare supervised and unsuperv ised debiasing methods\, emphasizing their underlying assumptions\, optimi zation objectives\, and practical trade-offs. The talk then addresses bias discovery and bias naming as foundational problems for systematic bias mi tigation. Finally\, we discuss emerging research directions\, including pr ivacy-aware debiasing\, fairness certification\, and machine unlearning\, highlighting open technical challenges and unresolved tensions between fai rness\, robustness\, and compliance.</div>\n<div>&nbsp\;</div>\n<div><stro ng data-removefontsize="true" data-originalcomputedfontsize="16">Bio:</str ong>\n<div><span data-removefontsize="true" data-originalcomputedfontsize= "16">Enzo Tartaglione is a Full Professor at T&eacute\;l&eacute\;com Paris \, where he is responsible for the equipe Multimedia and he is a Hi!Paris associate member. He is also a Member of the ELLIS Society\, Senior IEEE M ember\, Associate Editor of IEEE Transactions on Neural Networks and Learn ing Systems\, Action Editor for Transactions of Machine Learning Research and of the EURASIP Journal on Image and Video Processing. He received the MS degree in Electronic Engineering at Politecnico di Torino in 2015\, cum laude. The same year\, he also received a magna cum laude MS in electrica l and computer engineering at University of Illinois at Chicago. In 2016 h e was also awarded the MS in Electronics by Politecnico di Milano\, cum la ude. In 2019 he obtained a PhD in Physics at Politecnico di Torino\, cum l aude\, with the thesis "From Statistical Physics to Algorithms in Deep Neu ral Systems". His principal interests include compression and responsible (frugal) AI\, privacy-aware learning\, data debiasing\, and regularization for deep learning.</span></div>\n</div> END:VEVENT END:VCALENDAR