Patent · US Active

Training neural networks using mixed precision computations

US11741362B2 · kind B2 · utility

0Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 8, 2018
Grant dateAug 29, 2023
Priority date
Expiry dateOct 16, 2041

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH03M7/24
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system for training a neural network receives training data and performing lower precision format training calculations using lower precision format data at one or more training phases. One or more results from the lower precision format training calculations are converted to higher precision format data, and higher precision format training calculations are performed using the higher precision format data at one or more additional training phases. The neural network is modified using the results from the one or more additional training phases. The mixed precision format training calculations train the neural network more efficiently, while maintaining an overall accuracy.

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