Patent · US Active

System and method for increasing efficiency of gradient descent while training machine-learning models

US11763151B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventor

Key dates

Filing dateAug 18, 2021
Grant dateSep 19, 2023
Priority date
Expiry dateDec 9, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods of the present disclosure provide processes for determining how much to adjust machine-learning parameter values in a direction of a gradient for gradient-descent steps in training processes for machine-learning models. Current parameter values of a machine-learning model are vector components that define an initial estimate for a local extremum of a cost function used to measure how well the machine-learning model performs. The initial estimate and the gradient of the cost function for the initial estimate are used to define an auxiliary function. A root estimate is determined for the auxiliary function of the gradient. The parameters are adjusted in the direction of the gradient by an amount specified by the root estimate.

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