US Patent Issued to International Business Machines, Rensselaer Polytechnic Institute on Aug. 25 for "Designing ladder and laguerre orthogonal recurrent neural network architectures inspired by discrete-time dynamical systems" (New York Inventors)

ALEXANDRIA, Va., Aug. 25 -- United States Patent no. 12,718,088, issued on Aug. 25, was assigned to International Business Machines Corp. (Armonk, N.Y.) and Rensselaer Polytechnic Institute (Troy, N.Y.).

"Designing ladder and laguerre orthogonal recurrent neural network architectures inspired by discrete-time dynamical systems" was invented by Sergio Dorado (Yorktown Heights, N.Y.), Bhanukiran Vinzamuri (Long Island City, N.Y.) and Luigi Vanfretti (Troy, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method and system for making a prediction with a recurrent neural network (RNN) of a discrete-time linear time-invariant system can receive, as an input into a recurrent neural network cell, a memory flow...