BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250521T165843Z UID:44268ED1-A5FD-4F92-9706-893AF74AFC2C DTSTART;TZID=America/New_York:20250520T180000 DTEND;TZID=America/New_York:20250520T200000 DESCRIPTION:This talk provides an in-depth exploration into resource manage ment within 6G wireless networks\, focusing on the vision\, key performanc e indicators (KPIs)\, key enabling techniques (KETs)\, and the diverse arr ay of services characteristic of these advanced networks. The distinct cha llenges inherent in 6G's resource management call for a pivotal shift towa rds artificial intelligence (AI) and machine learning (ML)-driven solution s\, necessitating a departure from traditional optimization-centric approa ches. This talk will shed light on generative AI and unsupervised ML strat egies tailored to effectively address convex and non-convex resource manag ement optimization problems. A key focus will be on deep unsupervised lear ning techniques for network resource allocation\, addressing non-linear an d non-convex constraints. Deep implicit layers and differentiable projecti on methods will be explored as mechanisms to ensure zero constraint violat ions in applications such as beamforming\, phase-shift optimization\, and power allocation. Furthermore\, the potential of generative AI models\, in cluding large language models (LLMs)\, to enable proactive network resourc e allocation will be examined\, highlighting their role in optimizing perf ormance and reducing reliance on traditional heuristics. The session will conclude by identifying key research gaps and future directions\, paving t he way for next-generation AI-driven wireless networks.\n\nSpeaker(s): Dr. Hina Tabassum\, \n\nRoom: EV003-309\, Bldg: Electrical & Computer Enginee ring Department EV\, Concordia University\, 1515 Ste. Catherine West (corn er with Guy St.)\, MONTREAL\, Quebec\, Canada\, H3G 1M8 LOCATION:Room: EV003-309\, Bldg: Electrical & Computer Engineering Departme nt EV\, Concordia University\, 1515 Ste. Catherine West (corner with Guy S t.)\, MONTREAL\, Quebec\, Canada\, H3G 1M8 ORGANIZER:anader.benyamin@ieee.org SEQUENCE:21 SUMMARY:Generative AI and Deep Learning for Resource Allocation in 6G Wirel ess Networks URL;VALUE=URI:https://events.vtools.ieee.org/m/481970 X-ALT-DESC:Description: <br /><p>This talk provides an in-depth exploration into resource management within 6G wireless networks\, focusing on the vi sion\, key performance indicators (KPIs)\, key enabling techniques (KETs)\ , and the diverse array of services characteristic of these advanced netwo rks. The distinct challenges inherent in 6G's resource management call for a pivotal shift towards artificial intelligence (AI) and machine learning (ML)-driven solutions\, necessitating a departure from traditional optimi zation-centric approaches. This talk will shed light on generative AI and unsupervised ML strategies tailored to effectively address convex and non- convex resource management optimization problems. A key focus will be on d eep unsupervised learning techniques for network resource allocation\, add ressing non-linear and non-convex constraints. Deep implicit layers and di fferentiable projection methods will be explored as mechanisms to ensure z ero constraint violations in applications such as beamforming\, phase-shif t optimization\, and power allocation. Furthermore\, the potential of gene rative AI models\, including large language models (LLMs)\, to enable proa ctive network resource allocation will be examined\, highlighting their ro le in optimizing performance and reducing reliance on traditional heuristi cs. The session will conclude by identifying key research gaps and future directions\, paving the way for next-generation AI-driven wireless network s.</p> END:VEVENT END:VCALENDAR