US Patent Issued to Fraunhofer-Gesellschaft zur Forderung der angewandten Forschung on Aug. 25 for "Concepts for encoding and decoding neural network parameters" (German Inventors)

ALEXANDRIA, Va., Aug. 25 -- United States Patent no. 12,719,503, issued on Aug. 25, was assigned to Fraunhofer-Gesellschaft zur Forderung der angewandten Forschung e.V. (Munich).

"Concepts for encoding and decoding neural network parameters" was invented by Gerhard Tech (Berlin), Paul Haase (Berlin), Daniel Becking (Berlin), Heiner Kirchhoffer (Berlin), Jonathan Pfaff (Berlin), Karsten Muller (Berlin), Wojciech Samek (Berlin), Heiko Schwarz (Berlin), Detlev Marpe (Berlin) and Thomas Wiegand (Berlin).

According to the abstract* released by the U.S. Patent & Trademark Office: "Some embodiments relate to a method, a decoder and/or an encoder for entropy coding of parameters of neural networks and their incremental updates, and in particular ...