1 code implementation • 2 Mar 2021 • Kartik Hegde, Po-An Tsai, Sitao Huang, Vikas Chandra, Angshuman Parashar, Christopher W. Fletcher
The key idea is to derive a smooth, differentiable approximation to the otherwise non-smooth, non-convex search space.
no code implementations • 16 Oct 2018 • Kartik Hegde, Rohit Agrawal, Yulun Yao, Christopher W. Fletcher
Morph further achieves a 15. 9x average energy reduction on 3D CNNs when compared to Eyeriss.
no code implementations • 18 Apr 2018 • Kartik Hegde, Jiyong Yu, Rohit Agrawal, Mengjia Yan, Michael Pellauer, Christopher W. Fletcher
This paper studies how weight repetition ---when the same weight occurs multiple times in or across weight vectors--- can be exploited to save energy and improve performance during CNN inference.