US Patent Issued to Oracle International on April 21 for "Statistical confidence metric for reconstructive anomaly detection models" (Swiss, Canadian, American Inventors)

ALEXANDRIA, Va., April 21 -- United States Patent no. 12,608,601, issued on April 21, was assigned to Oracle International Corp. (Redwood Shores, Calif.).

"Statistical confidence metric for reconstructive anomaly detection models" was invented by Saeid Allahdadian (Vancouver, Canada), Matteo Casserini (Zurich), Andrew Brownsword (Vancouver, Canada), Amin Suzani (Vancouver, Canada), Milos Vasic (Zurich), Felix Schmidt (Niederweningen, Switzerland) and Nipun Agarwal (Saratoga, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Approaches herein relate to reconstructive models such as an autoencoder for anomaly detection. Herein are machine learning techniques that measure inference confidence based on recon...