•   When: Tuesday, March 17, 2020 from 01:00 PM to 02:00 PM
•   Speakers: Shuochao Yao
•   Location: ENGR 1605 or Online (contact host phpathak@gmu.edu for details on how to join online)
•   Export to iCal

Abstract: The Internet of Things (IoT) heralds the emergence of multitudes of computing-enabled networked everyday devices with sensing capabilities in homes, cars, workplaces, and on our persons, leading to ubiquitous smarter environments and smarter cyber-physical “things”. The next natural step in this computing evolution is to develop the infrastructure needed for these computational things to collectively learn. Bridging deep learning capabilities and IoT requires joint optimization of both AI algorithms and system designs to attain new points in the resulting complex trade-off landscape that are suitable for IoT applications. In this talk, I will discuss core challenges in (i) resource efficiency of machine inference to fit embedded devices, (ii) feature communication efficiency in distributed inference systems, (iii) scheduling of AI services, and (iv) accuracy of inference in CPS contexts.

Bio: Shuochao Yao is a postdoc researcher in Computer Science at University of Illinois at Urbana-Champaign, where he received his Ph.D. in 2019. His research lies in the system efficiency, human-resources efficiency, modelling, reliability, and related applications of deep learning enabled IoT/CPS. He is the recipient of the IMWUT (Volume 2) Distinguished Paper Award, the SenSys Best Paper Award Nominee (2017), and the ICCPS Best Paper Award (2017).