BIT WIDTH SELECTION FOR FIXED POINT NEURAL NETWORKS

摘要

A method for selecting bit widths for a fixed point machine learning model includes evaluating a sensitivity of model accuracy to bit widths at each computational stage of the model. The method also includes selecting a bit width for parameters, and/or intermediate calculations in the computational stages of the mode. The bit width for the parameters and the bit width for the intermediate calculations may be different. The selected bit width may be determined based on the sensitivity evaluation.

主权项

1. A method for selecting bit widths for a fixed point machine learning model, comprising:
evaluating a sensitivity of model accuracy to bit widths at each computational stage of the model; and selecting a bit width for one or more of parameters and intermediate calculations in the computational stages of the model based at least in part on the evaluating.