US Patent Issued to Huawei Technologies'Co., 'Ltd.' on April 29 for "Training method for quantizing the weights and inputs of a neural network" (Canadian Inventors)

ALEXANDRIA, Va., June 9 -- United States Patent no. 12,288,163, issued on April 29, was assigned to Huawei Technologies'Co.'Ltd.' (Shenzhen, China).

"Training method for quantizing the weights and inputs of a neural network" was invented by Vahid Partovi Nia (Montreal) and Ryan Razani (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method and processing unit for training a neural network to selectively quantize weights of a filter of the neural network as either binary weights or ternary weights. A plurality of training iterations a performed that each comprise: quantizing a set of real-valued weights of a filter to generate a corresponding set of quantized weights; generating an output feature ten...