BriefGPT.xyz
Feb, 2019
学习步长量化
Learned Step Size Quantization
HTML
PDF
Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, Dharmendra S. Modha
TL;DR
本研究提出了一种训练低精度神经网络的方法，Learned Step Size Quantization，该方法使用2、3或4位字长量化权重和激活函数，并能够训练3位模型达到完全精度基线准确性，在ImageNet数据集上实现了迄今为止最高的准确性。
Abstract
We present here Learned Step Size
quantization
, a method for
training
deep networks
such that they can run at inference time using
→