Patent · US Active

Memory-efficient backpropagation through time

US11256990B2 · kind B2 · utility

7Cited by
0References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 19, 2017
Grant dateFeb 22, 2022
Priority date
Expiry dateApr 28, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a recurrent neural network on training sequences using backpropagation through time. In one aspect, a method includes receiving a training sequence including a respective input at each of a number of time steps; obtaining data defining an amount of memory allocated to storing forward propagation information for use during backpropagation; determining, from the number of time steps in the training sequence and from the amount of memory allocated to storing the forward propagation information, a training policy for processing the training sequence, wherein the training policy defines when to store forward propagation information during forward propagation of the training sequence; and training the recurrent neural network on the training sequence in accordance with the training policy.

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