US Patent Issued to Google on June 2 for "Neural architecture scaling for hardware accelerators" (California, New York Inventors)

ALEXANDRIA, Va., June 2 -- United States Patent no. 12,645,910, issued on June 2, was assigned to Google LLC (Mountain View, Calif.).

"Neural architecture scaling for hardware accelerators" was invented by Andrew Li (Sunnyvale, Calif.), Sheng Li (Cupertino, Calif.), Mingxing Tan (Sunnyvale, Calif.), Ruoming Pang (New York), Liqun Cheng (Palo Alto, Calif.), Quoc V. Le (Sunnyvale, Calif.) and Norman Paul Jouppi (Palo Alto, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer-readable media, for scaling neural network architectures on hardware accelerators. A method includes receiving training data and information specifying target computing resources, and pe...