US Patent Issued to Intel on June 3 for "Hardened deep neural networks through training from adversarial misclassified data" (Oregon Inventors)

ALEXANDRIA, Va., June 4 -- United States Patent no. 12,322,165, issued on June 3, was assigned to Intel Corp. (Santa Clara, Calif.).

"Hardened deep neural networks through training from adversarial misclassified data" was invented by Li Chen (Hillsboro, Ore.) and Ravi L. Sahita (Portland, Ore.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Various embodiments are generally directed to techniques for training deep neural networks, such as with an iterative approach, for instance. Some embodiments are particularly directed to a deep neural network (DNN) training system that generates a hardened DNN by iteratively training DNNs with images that were misclassified by previous iterations of the DNN. One or more e...