ALEXANDRIA, Va., June 19 -- United States Patent no. 12,333,773, issued on June 17, was assigned to KONINKLIJKE PHILIPS N.V. (Eindhoven, Netherlands).
"Explaining a model output of a trained model" was invented by Bart Jacob Bakker (Eindhoven, Netherlands), Dimitrios Mavroeidis (Utrecht, Netherlands) and Stojan Trajanovski (London).
According to the abstract* released by the U.S. Patent & Trademark Office: "The invention relates a computer-implemented method (500) of generating explainability information for explaining a model output of a trained model. The method uses one or more aspect recognition models configured to indicate a presence of respective characteristics in the input instance. A saliency method is applied to obtain a masked...