ALEXANDRIA, Va., June 5 -- United States Patent no. 12,277,753, issued on April 15, was assigned to Reality Defender Inc. (New York).

"Common-sense bias discovery and mitigation for machine-learning tasks" was invented by Gaurav Bharaj (San Francisco), Miao Zhang (Jersey City, N.J.), Zee Fryer (Oakland, Calif.), Ben Colman (New York) and Ali Shahriyari (Las Vegas).

According to the abstract* released by the U.S. Patent & Trademark Office: "An exemplary method for reducing bias in a training image dataset for training a machine-learning model comprises: receiving a plurality of text strings comprising at least one text string describing each image in the training image dataset; generating a plurality of embeddings based on the plurality of...