US Patent Issued to International Business Machines on Feb. 3 for "Semi-supervised learning of training gradients via task generation" (Israeli Inventors)

ALEXANDRIA, Va., Feb. 3 -- United States Patent no. 12,541,685, issued on Feb. 3, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Semi-supervised learning of training gradients via task generation" was invented by Leonid Karlinsky (Mazkeret Batya, Israel) and Joseph Shtok (Binyamina, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "In an approach for augmenting a neural network with a self-supervised mechanism, a processor trains a first neural network using labeled data, the first neural network configured for a main task. A processor trains a second neural network using the labeled data and unlabeled data, the second neural network being an additional component to the first neur...