US Patent Issued to QUALCOMM on March 31 for "Dynamic quantization for energy efficient deep learning" (California, Texas Inventors)

ALEXANDRIA, Va., March 31 -- United States Patent no. 12,591,771, issued on March 31, was assigned to QUALCOMM Inc. (San Diego).

"Dynamic quantization for energy efficient deep learning" was invented by Randy Ardywibowo (Bryan, Texas), Venkata Ravi Kiran Dayana (San Diego) and Hau Hwang (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method performed by a deep neural network (DNN) includes receiving, at a layer of the DNN during an inference stage, a layer input comprising content associated with a DNN input received at the DNN. The method also includes quantizing one or more parameters of a plurality of parameters associated with the layer based on the content of the layer input. The method furt...