US Patent Issued to International Business Machines on Sept. 15 for "Machine learning model training with adversarial learning and triplet loss regularization" (New York Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,637, issued on Sept. 15, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Machine learning model training with adversarial learning and triplet loss regularization" was invented by Xuan-Hong Dang (Chappaqua, N.Y.), Dinesh C. Verma (New Castle, N.Y.), Seraphin Bernard Calo (Cortlandt Manor, N.Y.) and Petros Zerfos (New York).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method, computer system, and a computer program product for training a machine learning model are provided. A first set of labelled training data from a source domain is obtained. A second set of labelled training data from a target domain is obtained. A numbe...