US Patent Issued to ADOBE on Nov. 18 for "Machine unlearning and retraining of a machine learning model based on a modified training dataset" (Maryland, California Inventors)

ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,368, issued on Nov. 18, was assigned to ADOBE INC. (San Jose, Calif.).

"Machine unlearning and retraining of a machine learning model based on a modified training dataset" was invented by Enayat Ullah (Baltimore), Anup Bandigadi Rao (San Jose, Calif.), Tung Mai (San Jose, Calif.) and Ryan A. Rossi (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for training a neural network are described. One or more embodiments of the present disclosure include training a neural network based on a first combined gradient of a loss function at a plurality of sampled elements of a dataset; receiving an insertion request that indic...