ALEXANDRIA, Va., Dec. 2 -- United States Patent no. 12,488,242, issued on Dec. 2, was assigned to UMNAI Ltd. (Ta' Xbiex, Malta).
"Method for an explainable autoencoder and an explainable generative adversarial network" was invented by Angelo Dalli (Floriana, Malta), Mauro Pirrone (Kalkara, Malta) and Matthew Grech (San Gwann, Malta).
According to the abstract* released by the U.S. Patent & Trademark Office: "An exemplary embodiment provides an autoencoder which is explainable. An exemplary autoencoder may explain the degree to which each feature of the input attributed to the output of the system, which may be a compressed data representation. An exemplary embodiment may be used for classification, such as anomaly detection, as well as ot...