US Patent Issued to TELEFONAKTIEBOLAGET LM ERICSSON on Aug. 4 for "Decentralized federated machine-learning by selecting participating worker nodes" (Swedish Inventors)

ALEXANDRIA, Va., Aug. 5 -- United States Patent no. 12,699,880, issued on Aug. 4, was assigned to TELEFONAKTIEBOLAGET LM ERICSSON (PUBL) (Stockholm).

"Decentralized federated machine-learning by selecting participating worker nodes" was invented by Jalil Taghia (Stockholm), Farnaz Moradi (Stockholm), Selim Ickin (Stocksund, Sweden), Konstantinos Vandikas (Solna, Sweden) and Wenfeng Hu (Taby, Sweden).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, apparatuses and computer programs are presented for developing machine-learning models. A method for decentralized machine learning in a target worker node comprises: receiving a plurality of adapted neural network models from a plurality of worker n...