BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Hardware Datapath: For Machine Learning and Beyond - Professor Geo
 rge A. Constantinides - Professor of Digital Computation\, Department of E
 lectrical and Electronic Engineering\, Imperial College London
DTSTART:20250212T150500Z
DTEND:20250212T155500Z
UID:TALK225220@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:Abstract: We will explore a couple of topics of recent interes
 t to me: how to best bridge the Boolean world of hardware design with the 
 continuous world of modern machine learning\, and how to utilise recent ad
 vances in graph rewriting for datapath optimization. The former will lead 
 us to explore how the fundamental computational units of deep learning mig
 ht be reconsidered with hardware efficiency in mind. The latter will allow
  us to optimize  hardware for computer arithmetic\, including automated (r
 e-)discovery of well-known manual tricks\, and is now in use by Intel. Thi
 s talk summarises the outcomes of joint work with Marta Andronic\, Peter C
 heung\, Sam Coward\, James Davis\, Theo Drane and Erwei Wang.\n\nBio: Geor
 ge A. Constantinides received the Ph.D. degree from Imperial College Londo
 n in 2001. Since 2002\, he has been with the faculty at Imperial College L
 ondon\, where he is currently Professor of Digital Computation and Directo
 r of the Imperial Early Career Researcher Institute\, having previously se
 rved as Associate Dean of Engineering and Head of Circuits and Systems. He
  has been TPC chair of the FPGA\, FPL and FPT conferences. He currently se
 rves on several program committees and has published over 200 research pap
 ers in peer refereed journals and international conferences. Prof Constant
 inides enjoys family\, espresso and general geekery.\n\nLink to join virtu
 ally: https://cam-ac-uk.zoom.us/j/87421957265\n\nA recording of this talk 
 is available at the following link: https://www.cl.cam.ac.uk/seminars/wedn
 esday/video/\n\nThis talk is being recorded. If you do not wish to be seen
  in the recording\, please avoid sitting in the front three rows of seats 
 in the lecture theatre. Any questions asked will also be included in the r
 ecording. The recording will be made available on the Department’s webpa
 ge\n\nThis Wednesday Seminar will be followed by a Compiler Social. Please
  find further information and registration details at the following link: 
 https://grosser.science/compiler-social-2025-02-12/
LOCATION:Lecture Theatre 1\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR