US Patent Issued to ROBERT BOSCH on June 24 for "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" (German, American Inventors)

ALEXANDRIA, Va., June 25 -- United States Patent no. 12,340,572, issued on June 24, was assigned to ROBERT BOSCH GMBH (Stuttgart, Germany).

"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" was invented by Chaithanya Kumar Mummadi (Pittsburgh), Evgeny Levinkov (Stuttgart, Germany), Jan Hendrik Metzen (Boeblingen, Germany), Kilian Rambach (Stuttgart, Germany) and Robin Hutmacher (Renningen, Germany).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method for adapting a pretrained machine learning system, which has been trained on a first training d...