ALEXANDRIA, Va., July 16 -- United States Patent no. 12,361,280, issued on July 15, was assigned to Siemens Healthcare Diagnostics Inc. (Tarrytown, N.Y.).

"Method and device for training a machine learning routine for controlling a technical system" was invented by Markus Michael Geipel (Munich), Stefan Depeweg (Munich), Christoph Tietz (Ottobrunn, Germany), Gaby Marquardt (Hausen, Germany) and Daniela Seidel (Baiersdorf, Germany).

According to the abstract* released by the U.S. Patent & Trademark Office: "To train a machine learning routine (BNN), a sequence of first training data (PIC) is read in through the machine learning routine. The machine learning routine is trained using the first training data, wherein a plurality of learning p...