ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,783,859, issued on Nov. 3, was assigned to Robert Bosch GmbH (Stuttgart, Germany).

"Double descent for time series forecasting" was invented by Sam Heshmati (San Jose, Calif.), Burhaneddin Yaman (San Jose, Calif.) and Valentino Assandri (Berlin).

According to the abstract* released by the U.S. Patent & Trademark Office: "A "modern regime" training framework for deep learning-based time series forecasting models is described herein. In summary, the "modern regime" training framework consists of configuring the hyperparameters of the training process in a manner that substantially increases the complexity of the time series forecasting model beyond conventional norms and enables the tim...