ALEXANDRIA, Va., April 15 -- United States Patent no. 12,602,573, issued on April 14, was assigned to National Technology & Engineering Solutions of Sandia LLC (Albuquerque, N.M.).
"Neural network robustness via binary activation" was invented by William Mark Severa (Albuquerque, N.M.), Craig Michael Vineyard (Cedar Crest, N.M.), Ryan Anthony Dellana (Albuquerque, N.M.) and Abrar Anwar (Rosenberg, Texas).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method of increasing neural network robustness. The method comprises defining an artificial neural network comprising a number of bounded ramp activation functions. The network is trained iteratively in a layer-by-layer fashion. Each iteration increases the slo...