ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,399,952, issued on Aug. 26, was assigned to California Institute of Technology (Pasadena, Calif.).
"Resilience determination and damage recovery in neural networks" was invented by Guruprasad Raghavan (Pasadena, Calif.) and Matthew W. Thomson (Pasadena, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Disclosed herein include systems, devices, computer readable media, and methods for resilience determination and damage recovery in neural networks using a weight space and a metric that together form a manifold (such as a pseudo-Riemannian manifold or a Riemannian manifold)."
The patent was filed on June 16, 2021, under Application No. 17/349,743.
...