US Patent Issued to Oracle International on Dec. 9 for "Using generative adversarial networks to construct realistic counterfactual explanations for machine learning models" (Canadian, American Inventors)

ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,493,796, issued on Dec. 9, was assigned to Oracle International Corp. (Redwood Shores, Calif.).

"Using generative adversarial networks to construct realistic counterfactual explanations for machine learning models" was invented by Karoon Rashedi Nia (Vancouver, Canada), Tayler Hetherington (Vancouver, Canada), Zahra Zohrevand (Vancouver, Canada), Yasha Pushak (Vancouver, Canada), Sanjay Jinturkar (Santa Clara, Calif.) and Nipun Agarwal (Saratoga, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Herein are counterfactual explanations of machine learning (ML) inferencing provided by generative adversarial networks (GANs) that ensure realistic counterf...