US Patent Issued to International Business Machines on Sept. 9 for "Automatic hybrid quantization for deep neural network" (Chinese Inventors)

ALEXANDRIA, Va., Sept. 10 -- United States Patent no. 12,412,083, issued on Sept. 9, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Automatic hybrid quantization for deep neural network" was invented by Tao Wang (Beijing), Chang Xu (Beijing), Chao Xue (Beijing) and Qing Wang (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, computer program products, and/or systems are provided that perform the following operations: obtaining a target neural network structure and constraints for a target neural network; generating a meta learning network having an associated quantization function based, at least in part, on the target neural network structure; training the meta learning...