US Patent Issued to Intel on April 7 for "Optimizing low precision inference models for deployment of deep neural networks" (Chinese Inventors)

ALEXANDRIA, Va., April 7 -- United States Patent no. 12,596,917, issued on April 7, was assigned to Intel Corp. (Santa Clara, Calif.).

"Optimizing low precision inference models for deployment of deep neural networks" was invented by Jiong Gong (Shanghai), Yong Wu (Shanghai), Haihao Shen (Shanghai), Xiao Dong Lin (Shanghai), Guoming Zhang (Shanghai) and Feng Yuan (Shanghai).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, apparatuses and methods may provide technology for optimizing an inference neural network model that performs asymmetric quantization by generating a quantized neural network, wherein model weights of the neural network are quantized as signed integer values, and wherein an input laye...