ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,400,110, issued on Aug. 26, was assigned to Conti Temic Microelectronic GmbH (Nuremberg, Germany).
"Knowledge transfer between different deep learning architectures" was invented by Michelle Karg (Lindau, Germany) and Christian Scharfenberger (Lindau, Germany).
According to the abstract* released by the U.S. Patent & Trademark Office: "The invention relates to a method for converting a first neural network with a first architecture into a second neural network with a second architecture for use in a vehicle controller in order to obtain the knowledge of the first neural network and transfer same to the second neural network. In a first step of the method, a conversion (701) of at lea...