US Patent Issued to DeepMind Technologies on June 10 for "Using automatically uncovered failure cases to improve the performance of neural networks" (British, American Inventors)

ALEXANDRIA, Va., June 18 -- United States Patent no. 12,327,421, issued on June 10, was assigned to DeepMind Technologies Ltd. (London).

"Using automatically uncovered failure cases to improve the performance of neural networks" was invented by Ethan Josean Perez (Allen, Texas), Saffron Shan Huang (London), Nathaniel John McAleese-Park (London) and Geoffrey Irving (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting a target neural network using automatically generated test cases before deployment of the target neural network in a deployment environment. One of the methods may include generating...