Exploiting Typical Values to Accelerate Deep Learning

Andreas Moshovos, Jorge Albericio, Patrick Judd, Alberto Delmas Lascorz, Sayeh Sharify, Zissis Poulos, Tayler Hetherington, Tor Aamodt, Natalie Enright Jerger
2018 Computer  
To deliver the hardware computation power advances needed to support deep learning innovations, identifying deep learning properties that designers could potentially exploit is invaluable. This article articulates our strategy and overviews several value properties of deep learning models that we identified and some of our hardware designs that exploit them to reduce computation, and on-and off-chip storage and communication.
doi:10.1109/mc.2018.2381114 fatcat:zdhjauyvxfgd3lstj7ophamu7y