US Patent Issued to International Business Machines on May 20 for "Transfer anomaly detection using online deep sets" (Japanese Inventors)

ALEXANDRIA, Va., June 16 -- United States Patent no. 12,306,956, issued on May 20, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Transfer anomaly detection using online deep sets" was invented by Takayuki Katsuki (Tokyo), Haoxiang Qiu (Tokyo), Tadanobu Inoue (Yokohama, Japan) and Ryuki Tachibana (Tokyo).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computerized machine learning anomaly detection model trained on a plurality of samples of one or more source domains (optionally, one or more source domains and the target domain) is accessed. Using online deep sets, one or more domain vectors are computed for each target domain sample at an observation point, each target domain sample ...