US Patent Issued to Aptiv Technologies on April 14 for "Methods and systems for determining a representative input data set for post-training quantization of artificial neural networks" (German Inventors)

ALEXANDRIA, Va., April 15 -- United States Patent no. 12,602,585, issued on April 14, was assigned to Aptiv Technologies AG (Schaffhausen, Switzerland).

"Methods and systems for determining a representative input data set for post-training quantization of artificial neural networks" was invented by Robert Lajos Bucs (Wuppertal, Germany), Miguel Angel Aguilar (Dusseldorf, Germany) and Soeren Kreinberg (Wuppertal, Germany).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer implemented method for determining a representative input data set for post-training quantization of artificial neural networks comprises: acquiring an input data set; processing the input data set to extract one or more parameters ass...