BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Exceptional IEL seminar on Low-Power Analog Electronics: Fertilizi
 ng AI Revolution: From Data Acquisition to Connectivity
DTSTART:20210225T160000
DTEND:20210225T170000
DTSTAMP:20260916T063200Z
UID:20e12d542f333b7c674c44915c354f27745083eab0477339b2b90656
CATEGORIES:Conferences - Seminars
DESCRIPTION:Xiyuan Tang received the B.Sc. degree (Hons.) from the School 
 of Microelectronics\, Shanghai Jiao Tong University\, Shanghai\, China\, i
 n 2012\, and the M.S. and Ph.D. degree in electrical engineering from The 
 University of Texas at Austin\, Austin\, TX\, USA\, in 2014 and 2019 respe
 ctively\, where he is currently a post-doctoral researcher. He was a Desig
 n Engineer with Silicon Laboratories\, Austin\, from 2015 to 2017\, where 
 he was involved in the receiver design. The intellectual focus of his futu
 re research is on developing integrated circuit solutions to advance the d
 evelopment in emerging technologies\, with focus on IoT (e.g.\, intelligen
 t sensor)\, healthcare (e.g.\, low-cost monitor/diagnosis)\, and next-gene
 ration communication (e.g.\, 5G). Dr. Tang was a recipient of the IEEE Sol
 id-State Circuits Society Rising Stars in 2020 and Silicon Labs Tech Sympo
 sium Best Paper Award in 2016.\nAbstract: The artificial intelligence (AI)
  revolution has led to data explosion. As predicted\, global data traffic 
 will grow at approximately 30% each year. Given thermal and energy conside
 rations\, this exponentially increased data traffic implies a huge demand 
 for highly energy-efficient high-speed data links. Since this massive amou
 nt of data has to be harvested by billions of sensor front ends\, the batt
 ery life of the sensors becomes the most critical challenge to IoT growth\
 , in turn imposing stringent energy constraints for signal conditioning ci
 rcuits.  \nIn this talk\, I will first present integrated circuit techni
 ques that advance the energy-efficiency of the state-of-the-art data acqui
 sition systems. Subsequently\, I will introduce a low-cost reference stabi
 lization technique that significantly relaxes the reference settling requi
 rement for high-speed SAR ADCs. Finally\, in addition to circuit technique
 s\, I will also unveil latest developments in AI-assisted analog layout. B
 y leveraging computer vision techniques\, the trained AI can mimic an engi
 neer’s behavior and produce high-quality analog layouts.\n 
LOCATION:https://epfl.zoom.us/j/81153179432
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR