ALEXANDRIA, Va., Aug. 20 -- United States Patent no. 12,393,847, issued on Aug. 19, was assigned to MAGIC LEAP INC. (Plantation, Fla.).
"Gradient adversarial training of neural networks" was invented by Ayan Tuhinendu Sinha (San Francisco), Andrew Rabinovich (San Francisco), Zhao Chen (Mountain View, Calif.) and Vijay Badrinarayanan (Mountain View, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for gradient adversarial training of a neural network are disclosed. In one aspect of gradient adversarial training, an auxiliary neural network can be trained to classify a gradient tensor that is evaluated during backpropagation in a main neural network that provides a desired task output....