Patent · US Active

Fixed point neural network based on floating point neural network quantization

US10373050B2 · kind B2 · utility

16Cited by

5References

22Claims

0Family size

Assignee

QUALCOMM Incorporated · US

Inventors

Dexu Lin · San Diego, US
Venkata Sreekanta Reddy Annapureddy · San Diego, US
David E. Howard · Hazel Green, US
David Jonathan Julian · San Diego, US
Somdeb Majumdar · San Diego, US
William Richard Bell, II · Carlsbad, US

Key dates

Filing date	Oct 22, 2015
Grant date	Aug 6, 2019
Priority date	—
Expiry date	May 26, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/063
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method of quantizing a floating point machine learning network to obtain a fixed point machine learning network using a quantizer may include selecting at least one moment of an input distribution of the floating point machine learning network. The method may also include determining quantizer parameters for quantizing values of the floating point machine learning network based at least in part on the at least one selected moment of the input distribution of the floating point machine learning network to obtain corresponding values of the fixed point machine learning network.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.