US Patent Issued to International Business Machines on Feb. 17 for "Self-supervised learning of a task with normalization of nuisance from a different task" (Israeli Inventors)

ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,555,042, issued on Feb. 17, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Self-supervised learning of a task with normalization of nuisance from a different task" was invented by Hagai Aronowitz (Modiin, Israel) and Itai Gat (Tel-Aviv, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method including: obtaining a pre-trained upstream machine learning model; fine-tuning the pre-trained upstream model for at least two downstream tasks, wherein the fine-tuning comprises: (a) training a target downstream model for a target downstream task, based on a dataset with labeling specific to the target downstream...