US Patent Issued to AMAZON TECHNOLOGIES on Dec. 9 for "Machine learning model architecture for incremental asynchronous inference" (Washington Inventors)

ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,494,194, issued on Dec. 9, was assigned to AMAZON TECHNOLOGIES INC. (Seattle).

"Machine learning model architecture for incremental asynchronous inference" was invented by Joe Pemberton (Seattle), Vijitha Raji (Sammamish, Wash.), Jae Young Do (Kirkland, Wash.), Sahil Malik (Seattle) and Mohammad Kachuee (Bellevue, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Devices and techniques are generally described for incremental, asynchronous machine learning inference. In various examples, first feature data generated from a first process during a first time period may be input into a first subgraph of a neural network. Second feature data generated from...