US Patent Issued to Oracle International on Feb. 10 for "Entropy-based anti-modeling for machine learning applications" (Massachusetts Inventors)

ALEXANDRIA, Va., Feb. 11 -- United States Patent no. 12,547,894, issued on Feb. 10, was assigned to Oracle International Corp. (Redwood Shores, Calif.).

"Entropy-based anti-modeling for machine learning applications" was invented by Michael Louis Wick (Lexington, Mass.), Ariel Gedaliah Kobren (Cambridge, Mass.) and Swetasudha Panda (Burlington, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques are described herein for training and applying machine learning models. The techniques include implementing an entropy-based loss function for training high-capacity machine learning models, such as deep neural networks, with anti-modeling. The entropy-based loss function may cause the model to have high ...