US Patent Issued to Amazon Technologies on Oct. 6 for "Differentially private open-classification machine learning model training with adaptive clipping" (Washington, California Inventors)

ALEXANDRIA, Va., Oct. 6 -- United States Patent no. 12,755,517, issued on Oct. 6, was assigned to Amazon Technologies Inc. (Seattle).

"Differentially private open-classification machine learning model training with adaptive clipping" was invented by Yifan Xing (Kirkland, Wash.), Fanzi Wu (Bothell, Wash.), Jun Fang (Irvine, Calif.), Siqi Deng (Bellevue, Wash.), Aditya Sharad Golatkar (Los Angeles), Alessandro Achille (Arcadia, Calif.) and Dripta Sankar Raychaudhuri (Bellevue, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems for preserving privacy and maintaining performance of machine learning models by limiting an amount of noise and data that are added by an individual member of a tr...