US Patent Issued to International Business Machines on May 12 for "Reducing computational requirements for machine learning model explainability" (British, American Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,165, issued on May 12, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Reducing computational requirements for machine learning model explainability" was invented by Stefan A. G. Van Der Stockt (Austin, Texas), Erika Agostinelli (Bristol, Great Britain), Edward James Biddle (Winchester, Great Britain) and Sourav Mazumder (Contra Costa, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A first input transaction is classified into a first input space cluster in a set of input space clusters. It is determined that the first input space cluster maps to a single explainability space cluster in a set of explainability space clust...