ALEXANDRIA, Va., June 6 -- United States Patent no. 12,282,852, issued on April 22, was assigned to Intel Corp. (Santa Clara, Calif.).
"Dynamic quantization of neural networks" was invented by Michael E. Deisher (Hillsboro, Ore.).
According to the abstract* released by the U.S. Patent & Trademark Office: "An apparatus for applying dynamic quantization of a neural network is described herein. The apparatus includes a scaling unit and a quantizing unit. The scaling unit is to calculate an initial desired scale factors of a plurality of inputs, weights and a bias and apply the input scale factor to a summation node. Also, the scaling unit is to determine a scale factor for a multiplication node based on the desired scale factors of the input...