Patent · US Active

Population-based training of machine learning models

US11907821B2 · kind B2 · utility

0Cited by
1References
30Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 27, 2019
Grant dateFeb 20, 2024
Priority date
Expiry dateOct 26, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. A method includes: maintaining a plurality of training sessions; assigning, to each worker of one or more workers, a respective training session of the plurality of training sessions; repeatedly performing operations until meeting one or more termination criteria, the operations comprising: receiving an updated training session from a respective worker of the one or more workers, selecting a second training session, selecting, based on comparing the updated training session and the second training session using a fitness evaluation function, either the updated training session or the second training session as a parent training session, generating a child training session from the selected parent training session, and assigning the child training session to an available worker, and selecting a candidate model to be a trained model for the machine learning model.

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