US Patent Issued to Huawei Technologies on July 1 for "Generating a compressed representation of a neural network with proficient inference speed and power consumption" (California Inventors)

ALEXANDRIA, Va., July 3 -- United States Patent no. 12,346,803, issued on July 1, was assigned to Huawei Technologies Co. Ltd. (Shenzhen, China).

"Generating a compressed representation of a neural network with proficient inference speed and power consumption" was invented by Wei Wang (Santa Clara, Calif.) and Wei Jiang (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The disclosure relates to technology for generating a compressed neural network. A weight tensor is received from a neural network to be compressed, and it is reordered to be compressed to have an inner two-dimensional (2D) shape and a 2D sparse bitmap. A layered structure is generated that represents the reordered weight ten...