UPDF AI

Accurate and Efficient 2-bit Quantized Neural Networks

Jungwook Choi,Swagath Venkataramani,3 Authors,P. Chuang

2019 · DBLP: conf/mlsys/ChoiVSGWC19
USENIX workshop on Tackling computer systems problems with machine learning techniques · 166 Citations

TLDR

Novel techniques that individually target weight and activation quantizations resulting in an overall quantized neural network (QNN) are proposed that achieves state-of-the-art classification accuracy (comparable to full precision networks) across a range of popular models and datasets.