Patent · US Active

Processor and system to train machine learning models based on comparing accuracy of model parameters

US11804050B1 · kind B1 · utility

7Cited by

0References

16Claims

0Family size

Assignee

NVIDIA Corporation · US

Inventors

Fausto Milletari · Munich, DE
Maximilian Baust · Munich, DE
Nicola Christin Rieke · Munich, DE
Wenqi Li · Kunming, CN
Daguang Xu · Princeton, US
Andrew Feng · Cupertino, US
Rong-Shyang Ou · Palo Alto, US
Yan Cheng · Beijing, CN

Key dates

Filing date	Oct 31, 2019
Grant date	Oct 31, 2023
Priority date	—
Expiry date	Apr 21, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/105
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Apparatuses, systems, and techniques to collaboratively train one or more machine learning models. Parameter reviewers may be configured to compare sets of machine learning model parameter information in order to generate one or more machine learning models, such as neural networks.

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