US Patent Issued to AURORA OPERATIONS on Oct. 21 for "Compression of machine-learned models by vector quantization" (Canadian Inventors)

ALEXANDRIA, Va., Oct. 28 -- United States Patent no. 12,450,476, issued on Oct. 21, was assigned to AURORA OPERATIONS INC. (Pittsburgh).

"Compression of machine-learned models by vector quantization" was invented by Ting Wei Liu (Dollard-des-Ormeaux, Canada), Julieta Martinez Covarrubias (Toronto), Jashan Sunil Shewakramani (Waterloo, Canada), Raquel Urtasun (Toronto) and Wenyuan Zeng (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computing system can include one or more processors and one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the computing system to perform operations including obtaining model structure data indicative of a p...