Patent · US Active

Device and method to adapt a pretrained machine learning system to target data that has different distribution than the training data without the necessity of human annotations on target data

US12340572B2 · kind B2 · utility

0Cited by

0References

10Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Chaithanya Kumar Mummadi · Heimsheim, DE
Evgeny Levinkov · Stuttgart, DE
Jan Hendrik Metzen · Hessenhöfe, DE
Kilian Rambach · Stuttgart, DE
Robin Hutmacher · Renningen, DE

Key dates

Filing date	May 18, 2022
Grant date	Jun 24, 2025
Priority date	—
Expiry date	Aug 6, 2043

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/764
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A computer-implemented method for adapting a pretrained machine learning system, which has been trained on a first training data set, to a second dataset, wherein the second dataset has different characteristics than the first data set. An input transformation module for partly undoing the distribution shift between the first and second training data set is provided.

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