US Patent Issued to INAIT on Sept. 9 for "Characterizing activity in a recurrent artificial neural network" (Swiss, British Inventors)

ALEXANDRIA, Va., Sept. 10 -- United States Patent no. 12,412,072, issued on Sept. 9, was assigned to INAIT SA (Lausanne, Switzerland).

"Characterizing activity in a recurrent artificial neural network" was invented by Henry Markram (Lausanne, Switzerland), Ran Levi (Aberdeen, Great Britain) and Kathryn Pamela Hess Bellwald (Aigle, Switzerland).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for characterizing activity in a recurrent artificial neural network. In one aspect, a method includes outputting digits from a recurrent artificial neural network, wherein each digit represents whether or not activity within ...