BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240315T075622Z UID:330BA692-7545-4719-9F15-E7F313BCB1B1 DTSTART;TZID=America/Los_Angeles:20240314T173000 DTEND;TZID=America/Los_Angeles:20240314T183000 DESCRIPTION:Discover the future of edge AI in our upcoming talk by Dr. Jun Zhang\, an IEEE Fellow and Associate Professor at the Hong Kong University of Science and Technology. Delve into the shift from traditional data-ori ented communications to task-oriented approaches\, optimizing data transmi ssion for specific inference tasks. Learn about the development of effecti ve feature encoders and the introduction of EdgeGPT\, an autonomous edge A I system. This presentation will highlight innovations in edge video analy tics and mobile robotics\, offering insights into achieving high accuracy and low latency in resource-constrained devices. Join us to explore cuttin g-edge strategies for enhancing edge computing solutions.\n\nAt the time o f the meeting\, click here to Joint: https://simnet.zoom.us/j/98605376451? pwd=V0o0RmJDdTl3NU0yTDR6bjlNYm1Qdz09\n\nor manually using\nMeeting ID: 986 05376451\nMeeting Passcode: V0o0RmJDdTl3NU0yTDR6bjlNYm1Qdz09\n\nAbstract\n \nDeep learning has achieved remarkable successes in many application doma ins\, such as computer vision\, image processing\, and natural language pr ocessing. However\, deploying powerful deep learning models on resource-co nstrained mobile devices (e.g.\, wearable or IoT devices) faces great chal lenges. Recently\, edge AI techniques that rely on the emerging mobile edg e computing platforms have been proposed\, which forward intermediate feat ures to be processed by a powerful edge server. To achieve high-accuracy a nd low-latency inference\, effective feature encoders with low complexity and high compression capability will be needed. This calls for a paradigm shift in wireless communications\, from “data-oriented communications” \, which maximize data rates\, to “task-oriented communications”\, whe re the data transmission is an intermediate step to be optimized for the d ownstream inference task. This talk will introduce recent progresses on ta sk-oriented communication for edge inference. An effective design principl e based on information bottleneck will be firstly introduced\, which will then be extended to multi-device cooperative perception based on a distrib uted information bottleneck framework. Use cases on edge video analytics a nd edge-assisted localization for mobile robots will be presented\, follow ed by introduction of EdgeGPT\, an autonomous edge AI system empowered by large language models.\n\nBio:\n\nJun Zhang received his Ph.D. degree in E lectrical and Computer Engineering from the University of Texas at Austin. He is an IEEE Fellow and an IEEE ComSoc Distinguished Lecturer. He is an Associate Professor in the Department of Electronic and Computer Engineeri ng at the Hong Kong University of Science and Technology. His research int erests include wireless communications and networking\, mobile edge comput ing and edge AI\, and cooperative AI. Dr. Zhang co-authored the book Funda mentals of LTE (Prentice-Hall\, 2010). He is a co-recipient of several bes t paper awards\, including the 2021 Best Survey Paper Award of IEEE Commun ications Society\, the 2019 IEEE Communications Society & Information Theo ry Society Joint Paper Award\, and the 2016 Marconi Prize Paper Award in W ireless Communications. He also received the 2016 IEEE ComSoc Asia-Pacific Best Young Researcher Award. He is an Editor of IEEE Transactions on Comm unications and IEEE Transactions on Machine Learning in Communications and Networking\, and was an editor of IEEE Transactions on Wireless Communica tions (2015-2020).\n\nCo-sponsored by: Pradeep Kumar\n\nVirtual: https://e vents.vtools.ieee.org/m/406837 LOCATION:Virtual: https://events.vtools.ieee.org/m/406837 ORGANIZER:pradeep@ieee.org SEQUENCE:18 SUMMARY:Task-oriented Communications for Edge AI URL;VALUE=URI:https://events.vtools.ieee.org/m/406837 X-ALT-DESC:Description: <br /><p>Discover the future of edge AI in our upco ming talk by Dr. Jun Zhang\, an IEEE Fellow and Associate Professor at the Hong Kong University of Science and Technology. Delve into the shift from traditional data-oriented communications to task-oriented approaches\, op timizing data transmission for specific inference tasks. Learn about the d evelopment of effective feature encoders and the introduction of EdgeGPT\, an autonomous edge AI system. This presentation will highlight innovation s in edge video analytics and mobile robotics\, offering insights into ach ieving high accuracy and low latency in resource-constrained devices. Join us to explore cutting-edge strategies for enhancing edge computing soluti ons.</p>\n<p><strong><span style="color: rgb(53\, 152\, 219)\;">At the tim e of the meeting\, click here to Joint:</span> &nbsp\;<a href="https://sim net.zoom.us/j/98605376451?pwd=V0o0RmJDdTl3NU0yTDR6bjlNYm1Qdz09">https://si mnet.zoom.us/j/98605376451?pwd=V0o0RmJDdTl3NU0yTDR6bjlNYm1Qdz09</a></stron g></p>\n<p><span style="color: rgb(230\, 126\, 35)\;">or manually using<br ></span><span style="color: rgb(230\, 126\, 35)\;">Meeting ID:&nbsp\;<span class="ui-provider ed axw axx axy axz aya ayb ayc ayd aye ayf ayg ayh ayi ayj ayk ayl aym ayn ayo ayp ayq ayr ays ayt ayu ayv ayw ayx ayy ayz aza a zb azc azd" dir="ltr">98605376451<br>Meeting Passcode: V0o0RmJDdTl3NU0yTDR 6bjlNYm1Qdz09</span></span></p>\n<p><strong>Abstract</strong></p>\n<p>Deep learning has achieved remarkable successes in many application domains\, such as computer vision\, image processing\, and natural language processi ng. However\, deploying powerful deep learning models on resource-constrai ned mobile devices (e.g.\, wearable or IoT devices) faces great challenges . Recently\, edge AI techniques that rely on the emerging mobile edge comp uting platforms have been proposed\, which forward intermediate features t o be processed by a powerful edge server. To achieve high-accuracy and low -latency inference\, effective feature encoders with low complexity and hi gh compression capability will be needed. This calls for a paradigm shift in wireless communications\, from &ldquo\;data-oriented communications&rdq uo\;\, which maximize data rates\, to &ldquo\;task-oriented communications &rdquo\;\, where the data transmission is an intermediate step to be optim ized for the downstream inference task. This talk will introduce recent pr ogresses on task-oriented communication for edge inference. An effective d esign principle based on information bottleneck will be firstly introduced \, which will then be extended to multi-device cooperative perception base d on a distributed information bottleneck framework. Use cases on edge vid eo analytics and edge-assisted localization for mobile robots will be pres ented\, followed by introduction of EdgeGPT\, an autonomous edge AI system empowered by large language models.</p>\n<p><strong>Bio</strong>:</p>\n<p >Jun Zhang received his Ph.D. degree in Electrical and Computer Engineerin g from the University of Texas at Austin. He is an IEEE Fellow and an IEEE ComSoc Distinguished Lecturer. He is an Associate Professor in the Depart ment of Electronic and Computer Engineering at the Hong Kong University of Science and Technology. His research interests include wireless communica tions and networking\, mobile edge computing and edge AI\, and cooperative AI. Dr. Zhang co-authored the book Fundamentals of LTE (Prentice-Hall\, 2 010). He is a co-recipient of several best paper awards\, including the 20 21 Best Survey Paper Award of IEEE Communications Society\, the 2019 IEEE Communications Society &amp\; Information Theory Society Joint Paper Award \, and the 2016 Marconi Prize Paper Award in Wireless Communications. He a lso received the 2016 IEEE ComSoc Asia-Pacific Best Young Researcher Award . He is an Editor of IEEE Transactions on Communications and IEEE Transact ions on Machine Learning in Communications and Networking\, and was an edi tor of IEEE Transactions on Wireless Communications (2015-2020).</p> END:VEVENT END:VCALENDAR