BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260815T233748Z UID:7823D9D7-DB32-4235-8B5C-6B4F5C7D7484 DTSTART;TZID=America/Los_Angeles:20260901T150000 DTEND;TZID=America/Los_Angeles:20260901T183000 DESCRIPTION:In this talk\, we review sample results based on our recent wor k in the areas of machine learning\nover networks and edge intellligence. In particular\, we touch upon our work on communication-efficient federate d learning and its applications.\nIn the first part of the talk\, we shed light on topics pertaining to federated learning. First\, we overview a se cond-order federated learning algorithm\, coined Fed-Sophia\, with communi cation and computation efficiency merits. Next\, we introduce our recent w ork on second order state synchronization (SOSS) to address the limitation s of Fed-Sophia with non-IID data. Afterwards we overview MIRA which propo ses a novel approach of federated multi-task learning for fine-tuning LLMs .\nIn the second part of the talk\, we shift focus to edge intelligence ap plications in digital health with particular focus on CVD prediction. Fina lly\, we present our work on architecting\, designing and demonstrating a system prototype for multi-tier intelligence for IoT.\n\nSpeaker(s): Dr. T amer ElBatt\n\nAgenda: \n3 PM to 4 PM: Networking\n4 PM to 4:45 PM: Presen tation\n\n4:45 PM to 5:30 PM: Q&A\n\n5:30 PM to 6:30 PM: Networking\n\nRoo m: 1308\, Bldg: Sobrato Campus for Discovery and Innovation\, 500 El Camin o Real\, Santa Clara\, California\, United States\, 95053 LOCATION:Room: 1308\, Bldg: Sobrato Campus for Discovery and Innovation\, 5 00 El Camino Real\, Santa Clara\, California\, United States\, 95053 ORGANIZER:bdezfouli@scu.edu SEQUENCE:8 SUMMARY:Machine Learning over Networks: From Fundamentals to Applications. URL;VALUE=URI:https://events.vtools.ieee.org/m/572755 X-ALT-DESC:Description: <br /><p>In this talk\, we review sample results ba sed on our recent work in the areas of machine learning<br>over networks a nd edge intellligence. In particular\, we touch upon our work on communica tion-efficient federated learning and its applications.<br>In the first pa rt of the talk\, we shed light on topics pertaining to federated learning. First\, we overview a second-order federated learning algorithm\, coined Fed-Sophia\, with communication and computation efficiency merits. Next\, we introduce our recent work on second order state synchronization (SOSS) to address the limitations of Fed-Sophia with non-IID data. Afterwards we overview MIRA which proposes a novel approach of federated multi-task lear ning for fine-tuning LLMs.<br>In the second part of the talk\, we shift fo cus to edge intelligence applications in digital health with particular fo cus on CVD prediction. Finally\, we present our work on architecting\, des igning and demonstrating a system prototype for multi-tier intelligence fo r IoT.</p><br /><br />Agenda: <br /><div><strong>3 PM to 4 PM: Networking< /strong></div>\n<div><strong>4 PM to 4:45 PM: Presentation<br></strong></d iv>\n<div><strong>4:45 PM to 5:30 PM: Q&amp\;A<br></strong></div>\n<div><s trong>5:30 PM to 6:30 PM: Networking</strong></div> END:VEVENT END:VCALENDAR