Patent · US Active

Mixed-precision neural networks

US12015526B2 · kind B2 · utility

0Cited by
0References
17Claims
0Family size

Assignee

Inventor

Key dates

Filing dateApr 30, 2021
Grant dateJun 18, 2024
Priority date
Expiry dateFeb 7, 2042

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L41/0896
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques for mixed precision quantization of a machine learning (ML) model. A target bandwidth increase is received (302), for the ML model (114) including objects of a first data type represented by a first number of bits. The target bandwidth increase relates to changing a first portion of the objects to a second data type represented by a second number of bits different from the first number of bits (310). The method further includes sorting the objects in the ML model based on bandwidth (304). The method further includes identifying the first portion of the objects to change from the first data type to the second data type, based on the target bandwidth increase and the sorting of the plurality of objects (508). The method further includes changing the first portion of the objects from the first data type to the second data type (508).

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