Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:PDIQ4RMMrecord.jsonopen to challenge →
classification
cs.LG
cs.CV
keywords
networksneuraltrainingadaptivebackfixed-pointnumbersprecision
read the original 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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.