BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260606T023907Z UID:541E3E37-F950-4E81-BAF4-96A90B376A90 DTSTART;TZID=America/Chicago:20260527T180000 DTEND;TZID=America/Chicago:20260527T200000 DESCRIPTION:Self-supervised learning deals with problems that have little o r no available labeled data. Recent work has shown impressive results when underlying classes have significant semantic differences. We will discuss strategies to tackle to enable learning from unlabeled data even when sam ples from different classes are not prominently diverse. We approach the p roblem by leveraging novel ensemble-based clustering strategies where clus ters derived from different configurations are combined to generate a bett er grouping for the data samples in a fully-unsupervised way. We will see results for Person Re-Identification and Text Authorship Verification but the techniques are useful in other applications as well. Moreover\, we als o detail recent efforts on Causal Analysis to refine AI methods.\n\nAnders on Rocha (F) is a Full Professor of Artificial Intelligence and Digital Fo rensics at the Institute of Computing\, University of Campinas (Unicamp)\, Brazil. He is the head of the Artificial Intelligence Lab.\, Recod.ai\, a t Unicamp and was the former Director of the Institute for the 2019-2023 t erm. He holds a bachelor's degree in Computer Science (2003) from Federal University of Lavras\, Brazil\, a Masters Degree in Computer Science (2006 ) from Unicamp and a Ph.D. degree in Computer Science (2009) also from Uni camp\, Brazil.\n\nProf. Rocha is an elected affiliate of the Brazilian Aca demy of Sciences (ABC) and the Brazilian Academy of Forensic Sciences (ABC ). He is a three-term elected member of the IEEE Information Forensics and Security Technical Committee (IFS-TC\, 2011-2013\, 2014-2016\, 2023-2026) and a two-term former Chair of such committee (2015-2016\, 2025-2026). He is a Microsoft Research (2011) and a Google (2017-2022) Research Faculty Fellow\, an IEEE Fellow (2023)\, and IEEE Biometrics Distinguished Lecture r (2025-2027). In addition\, in 2016\, he was awarded the Tan Chin Tuan (T CT) Fellowship\, and the Asia Pacific Artificial Intelligence Association Fellowship.\n\nProf. Rocha has been the principal investigator of several research projects in partnership with public funding agencies in Brazil an d abroad and national and multi-national companies\, having already filed and licensed several patents. He is a Brazilian CNPq research scholar (PQ1 C). Finally\, he is now a LinkedIn Top Voice in Artificial Intelligence fo r continuously raising awareness of Al and its potential impacts on societ y at large.\n\n[Anderson Rocha](mailto:arrocha@unicamp.br)\n\nRoom: 302\, Bldg: Madison Central Library\, 201 West Mifflin Street\, Madison\, Wiscon sin\, United States\, 53703\, Virtual: https://events.vtools.ieee.org/m/55 8706 LOCATION:Room: 302\, Bldg: Madison Central Library\, 201 West Mifflin Stree t\, Madison\, Wisconsin\, United States\, 53703\, Virtual: https://events. vtools.ieee.org/m/558706 ORGANIZER:harrison@glsan.com SEQUENCE:19 SUMMARY:Reasoning for Complex Data through Self-Supervised Learning and Cau sality Discovery URL;VALUE=URI:https://events.vtools.ieee.org/m/558706 X-ALT-DESC:Description: <br /><p>Self-supervised learning deals with proble ms that have little or no available labeled data. Recent work has shown im pressive results when underlying classes have significant semantic differe nces. We will discuss strategies to tackle to enable learning from unlabel ed data even when samples from different classes are not prominently diver se. We approach the problem by leveraging novel ensemble-based clustering strategies where clusters derived from different configurations are combin ed to generate a better grouping for the data samples in a fully-unsupervi sed way. We will see results for Person Re-Identification and Text Authors hip Verification but the techniques are useful in other applications as we ll. Moreover\, we also detail recent efforts on Causal Analysis to refine AI methods.</p>\n<p>&nbsp\;</p>\n<p>Anderson Rocha (F) is a Full Professor of Artificial Intelligence and Digital Forensics at the Institute of Comp uting\, University of Campinas (Unicamp)\, Brazil. He is the head of the A rtificial Intelligence Lab.\, Recod.ai\, at Unicamp and was the former Dir ector of the Institute for the 2019-2023 term. He holds a bachelor's degre e in Computer Science (2003) from Federal University of Lavras\, Brazil\, a Masters Degree in Computer Science (2006) from Unicamp and a Ph.D. degre e in Computer Science (2009) also from Unicamp\, Brazil.&nbsp\;<br><br>Pro f. Rocha is an elected affiliate of the Brazilian Academy of Sciences (ABC ) and the Brazilian Academy of Forensic Sciences (ABC). He is a three-term elected member of the IEEE Information Forensics and Security Technical C ommittee (IFS-TC\, 2011-2013\, 2014-2016\, 2023-2026) and a two-term forme r Chair of such committee (2015-2016\, 2025-2026). He is a Microsoft Resea rch (2011) and a Google (2017-2022) Research Faculty Fellow\, an IEEE Fell ow (2023)\, and IEEE Biometrics Distinguished Lecturer (2025-2027). &nbsp\ ;In addition\, in 2016\, he was awarded the Tan Chin Tuan (TCT) Fellowship \, and the Asia Pacific Artificial Intelligence Association Fellowship.</p >\n<p>Prof. Rocha has been the principal investigator of several research projects in partnership with public funding agencies in Brazil and abroad and national and multi-national companies\, having already filed and licen sed several patents. He is a Brazilian CNPq research scholar (PQ1C). Final ly\, he is now a LinkedIn Top Voice in Artificial Intelligence for continu ously raising awareness of Al and its potential impacts on society at larg e.</p>\n<p><a class="mailto" href="mailto:arrocha@unicamp.br" data-extlink ="" aria-label="(link sends email)">Anderson Rocha</a>&nbsp\;</p> END:VEVENT END:VCALENDAR