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:20250524T013055Z
UID:BE51888B-0B1D-4782-A270-9681AA514E4F
DTSTART;TZID=America/New_York:20250520T180000
DTEND;TZID=America/New_York:20250520T200000
DESCRIPTION:Abstract :\n\nThis talk provides an in-depth exploration into r
 esource management within 6G wireless networks\, focusing on the vision\, 
 key performance indicators (KPIs)\, key enabling techniques (KETs)\, and t
 he diverse array of services characteristic of these advanced networks. Th
 e distinct challenges inherent in 6G's resource management call for a pivo
 tal shift towards artificial intelligence (AI) and machine learning (ML)-d
 riven solutions\, necessitating a departure from traditional optimization-
 centric approaches. This talk will shed light on generative AI and unsuper
 vised ML strategies tailored to effectively address convex and non-convex 
 resource management optimization problems. A key focus will be on deep uns
 upervised learning techniques for network resource allocation\, addressing
  non-linear and non-convex constraints. Deep implicit layers and different
 iable projection methods will be explored as mechanisms to ensure zero con
 straint violations in applications such as beamforming\, phase-shift optim
 ization\, and power allocation. Furthermore\, the potential of generative 
 AI models\, including large language models (LLMs)\, to enable proactive n
 etwork resource allocation will be examined\, highlighting their role in o
 ptimizing performance and reducing reliance on traditional heuristics. The
  session will conclude by identifying key research gaps and future directi
 ons\, paving the way for next-generation AI-driven wireless networks.\n\nC
 o-sponsored by: Reza Soleymani\n\nSpeaker(s): \, Dr. Tabassum\n\nRoom: EV0
 03-309\, Bldg: Electrical & Computer Engineering Department\, 1515 Ste. Ca
 therine West (corner with Guy St.)\, Concordia University\, Montreal\, Que
 bec\, Canada\, H3G 1M8
LOCATION:Room: EV003-309\, Bldg: Electrical & Computer Engineering Departme
 nt\, 1515 Ste. Catherine West (corner with Guy St.)\, Concordia University
 \, Montreal\, Quebec\, Canada\, H3G 1M8
ORGANIZER:anader.benyamin@ieee.org
SEQUENCE:25
SUMMARY:Generative AI and Deep Learning for Resource Allocation in 6G Wirel
 ess Networks
URL;VALUE=URI:https://events.vtools.ieee.org/m/479292
X-ALT-DESC:Description: <br /><p class="Default" style="margin-bottom: 1.0p
 t\;"><strong><u><span lang="EN-US" style="font-size: 11.0pt\; color: navy\
 ;">Abstract :</span></u></strong></p>\n<p class="MsoNormal" style="text-al
 ign: justify\; line-height: 115%\; mso-pagination: none\; mso-layout-grid-
 align: none\; text-autospace: none\; margin: .7pt 4.35pt .0001pt 0in\;"><s
 pan style="font-family: 'Arial'\,sans-serif\; color: black\;">&nbsp\;</spa
 n></p>\n<p class="MsoNormal" style="text-align: justify\; line-height: 115
 %\; mso-pagination: none\; mso-layout-grid-align: none\; text-autospace: n
 one\; margin: .7pt 4.35pt .0001pt 0in\;"><span style="font-family: 'Arial'
 \,sans-serif\; color: black\;">This talk provides an in-depth exploration 
 into resource management within 6G wireless networks\, focusing on the vis
 ion\, key performance indicators (KPIs)\, key enabling techniques (KETs)\,
  and the diverse array of services characteristic of these advanced networ
 ks. 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 optimiz
 ation-centric approaches. This talk will shed light on generative AI and u
 nsupervised ML strategies tailored to effectively address convex and non-c
 onvex resource management optimization problems.&nbsp\;A key focus will be
  on deep unsupervised learning techniques&nbsp\;for network resource alloc
 ation\, addressing non-linear and non-convex constraints. Deep implicit la
 yers and differentiable projection methods&nbsp\;will be explored as mecha
 nisms to ensure zero constraint violations in applications such as beamfor
 ming\, phase-shift optimization\, and power allocation.&nbsp\;Furthermore\
 , the potential of generative AI models\, including large language models 
 (LLMs)\, to enable proactive network resource allocation&nbsp\;will be exa
 mined\, highlighting their role in optimizing performance and reducing rel
 iance on traditional heuristics. The session will conclude by identifying 
 key research gaps and future directions\, paving the way for next-generati
 on AI-driven wireless networks.</span></p>
END:VEVENT
END:VCALENDAR