ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,588, issued on Sept. 15, was assigned to NVIDIA Corp. (Santa Clara, Calif.).
"Dynamic weight updates for neural networks" was invented by Holger Reinhard Roth (Rockville, Md.), Yingda Xia (Baltimore), Daguang Xu (Potomac, Md.), Andriy Myronenko (San Mateo, Calif.), Wenqi Li (London) and Dong Yang (Pocatello, Idaho).
According to the abstract* released by the U.S. Patent & Trademark Office: "Apparatuses, systems, and techniques to improve federated learning for neural networks. In at least one embodiment, a federated server dynamically selects neural network weights according to one or more learnable aggregation weights indicating a contribution from each of one or more edge devi...