US Patent Issued to Robert Bosch on Sept. 15 for "Regularised training of neural networks" (German Inventor)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,620, issued on Sept. 15, was assigned to Robert Bosch GmbH (Stuttgart, Germany).

"Regularised training of neural networks" was invented by Jens Eric Markus Mehnert (Malmsheim, Germany).

According to the abstract* released by the U.S. Patent & Trademark Office: "Training an artificial neural network, ANN, which translates one or more input variables into one or more output variables, using learning data sets including learning input variable values having measurement data, and associated learning output variable values, by: mapping learning input variable values from a learning data set onto output variable values using the ANN; processing deviations of the output variable values...