SOTAVerified

Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

2019-11-01Unverified0· sign in to hype

Xishan Zhang, Shaoli Liu, Rui Zhang, Chang Liu, Di Huang, Shiyi Zhou, Jiaming Guo, Yu Kang, Qi Guo, Zidong Du, Yunji Chen

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers. Recent emerged quantization technique has been applied to inference of deep neural networks for fast and efficient execution. However, directly applying quantization in training can cause significant accuracy loss, thus remaining an open challenge.

Tasks

Reproductions