US Patent Issued to HANGZHOU HIKVISION DIGITAL TECHNOLOGY on Sept. 22 for "Method for training neural network model based on power exponential domain fixed-point encoding" (Chinese Inventors)

ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,624, issued on Sept. 22, was assigned to HANGZHOU HIKVISION DIGITAL TECHNOLOGY Co. LTD. (Hangzhou, China).

"Method for training neural network model based on power exponential domain fixed-point encoding" was invented by Yuan Zhang (Hangzhou, China), Di Xie (Hangzhou, China) and Shiliang Pu (Hangzhou, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "The embodiments of the present disclosure provides a method and an apparatus for training a neural network model, A training sample is obtained, and the neural network model is trained using the training sample. When the neural network model is trained, power exponential domain fixed-point encoding ...