Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
Xishan Zhang, Shaoli Liu, Rui Zhang, Chang Liu, Di Huang, Shiyi Zhou, Jiaming Guo, Kang, Yu, Qi Yong Guo, Zidong Du, Yunji Chen · arXiv (Cornell University) · 2019
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.