US Patent Issued to ZHEJIANG UNIVERSITY on April 8 for "Neural network acceleration and neural network acceleration method based on structured pruning and low-bit quantization" (Chinese Inventors)

ALEXANDRIA, Va., April 9 -- United States Patent no. 12,271,820, issued on April 8, was assigned to ZHEJIANG UNIVERSITY (Hangzhou, China).

"Neural network acceleration and neural network acceleration method based on structured pruning and low-bit quantization" was invented by Kejie Huang (Zhejiang, China), Chaoyang Zhu (Zhejiang, China) and Haibin Shen (Zhejiang, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present invention discloses a neural network accelerator and a neural network acceleration method based on structured pruning and low-bit quantization. The neural network accelerator includes a master controller, an activations selection unit, an extensible calculation array, a multifunctional...