ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,425,044, issued on Sept. 23, was assigned to ATOMBEAM TECHNOLOGIES INC. (Moraga, Calif.).

"Federated large codeword model deep learning architecture" was invented by Brian Galvin (Silverdale, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system and method for a federated deep learning platform utilizing homomorphically-compressed and encrypted data. The system comprises multiple client devices, each with a local dataset, and a central server hosting a deep learning core. Client devices convert local data into codewords, which are also homomorphically encrypted. The central server processes these encrypted codewords without decryption, preservi...