BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//TECoSA - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:TECoSA
X-ORIGINAL-URL:https://www.tecosa.center.kth.se
X-WR-CALDESC:Events for TECoSA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20210101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20221103T150000
DTEND;TZID=UTC:20221103T160000
DTSTAMP:20260608T083957
CREATED:20220803T124516Z
LAST-MODIFIED:20221025T112450Z
UID:5355-1667487600-1667491200@www.tecosa.center.kth.se
SUMMARY:TECoSA Seminar - Efficient Inference at the Edge
DESCRIPTION:We aim to bring you a TECoSA Seminar on the first Thursday of each month during term-time. For Autumn 2022\, the talks will be on-line or hybrid. All are welcome to attend and we look forward to some lively discussions. Members can accept the invitations\, non-members can email vickid @ kth.se to register.\nOur November seminar is with Professor Axel Jantsch\, Professor of systems on chips at TU Wien.  The session is co-hosted with Digital Futures\, and will be given via Zoom (https://kth-se.zoom.us/j/66857695267)\, with a number of seats available in real life on KTH Campus (Digital Futures Conference Room\, Osquars backe 5\, SE-114 28 Stockholm).  Please email vickid @ kth.se by 31 October if you plan to join in real life. \nABSTRACT:  The presentation will review the design space\, the trade-offs and the available options for implementing Deep Neural Networks in resource constrained embedded devices.  Going into depth\, the talk will present:\n~ a detailed\, layer-wise power and delay profiling of neural network inference\, and\n~ pruning based network compression techniques. \nBIO: Axel Jantsch received the Ph.D. degree from TU Wien\, Vienna\, Austria\, in 1992. From 2002 to 2014\, he was a full professor in      electronic systems design at KTH. Since 2014\, he has been a Professor of systems on chips at TU Wien\, Vienna\, Austria.  His current research interests include systems on chips\, self-aware cyber-physical systems\, and embedded machine learning.  You can read more on his homepage: https://jantsch.se/AxelJantsch/HomePage/research.html \nThis event is co-sponsored by Digital Futures (www.digitalfutures.kth.se)
URL:https://www.tecosa.center.kth.se/event/tecosa-seminar-efficient-inference-at-the-edge/
CATEGORIES:Talks
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20221114T100000
DTEND;TZID=UTC:20221114T110000
DTSTAMP:20260608T083957
CREATED:20221101T123721Z
LAST-MODIFIED:20221101T123721Z
UID:5517-1668420000-1668423600@www.tecosa.center.kth.se
SUMMARY:How does edge AI change the principles of communications and computing?
DESCRIPTION:A Digital Futures Distinguished lecture with Kaibin Huang from The University of Hong Kong\nAbstract: Data has replaced oil as the world’s most valuable resource. An enormous amount of data is being generated 24/7 by tens of billions of edge devices at the network edge. Their distillation into AI using machine learning algorithms promises to automate practically unlimited IoT applications ranging from autonomous driving to virtual reality. This gives rise to a hot area known as edge intelligence\, a distinctive feature of 6G mobile networks. \nThree questions will be asked to understand the induced paradigm shift in communications:\n1) Is reliable communication always needed?\n2) Is interference always a foe?\n3) Is analogue computing outdated? \nProf Huang will introduce some 6G edge-intelligence technologies that feature communication-computing fusion to find negative answers to these questions. They include channel-noise protected/accelerated edge AI\, over-the-air federated learning\, and neuromorphic computing-empowered ultra-fast baseband processing. \nYou can find Prof Huang’s bio and the Zoom link at: https://www.digitalfutures.kth.se/event/distinguished-lecture-kaibin-huang-the-university-of-hong-kong/ 
URL:https://www.tecosa.center.kth.se/event/how-does-edge-ai-change-the-principles-of-communications-and-computing/
CATEGORIES:Talks
END:VEVENT
END:VCALENDAR