System and method for increasing efficiency of gradient descent while training machine-learning models
US11126893B1 · kind B1 · utility
Assignee
Inventor
Key dates
| Filing date | May 4, 2018 |
| Grant date | Sep 21, 2021 |
| Priority date | — |
| Expiry date | Jun 10, 2040 |
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.