US Patent Issued to Google on Nov. 18 for "Quantizing trained long short-term memory neural networks" (California Inventor)

ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,355, issued on Nov. 18, was assigned to Google LLC (Mountain View, Calif.).

"Quantizing trained long short-term memory neural networks" was invented by Raziel Alvarez Guevara (Menlo Park, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Method for quantizing a trained long short-term memory (LSTM) neural network having a plurality of weights, the method comprising: obtaining data specifying trained floating-point values for each of the weights of the trained LSTM neural network, the trained LSTM neural network comprising one or more LSTM layers, each LSTM layer having a plurality of gates and each of the plurality of gates being associated with...