ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,614, issued on Sept. 23, was assigned to International Business Machines Corp. (Armonk, N.Y.).
"Faithful and efficient sample-based model explanations" was invented by Yada Zhu (Irvington, N.Y.), Wei Zhang (Acton, Mass.), Guangnan Ye (Scarsdale, N.Y.) and Xiaodong Cui (Chappaqua, N.Y.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Hessian matrix-free sample-based techniques for model explanations that are faithful to the model are provided. In one aspect, a method for explaining a machine learning model {circumflex over (Theta)} (e.g., for natural language processing) is provided. The method includes: training the machine learning model {circumflex...