ALEXANDRIA, Va., Jan. 28 -- United States Patent no. 12,536,418, issued on Jan. 27, was assigned to Carnegie Mellon University (Pittsburgh).
"Perturbative neural network" was invented by Felix Juefei Xu (Pittsburgh) and Marios Savvides (Pittsburgh).
According to the abstract* released by the U.S. Patent & Trademark Office: "Perturbative neural networks are comprised of one or more modules, called perturbation layers which can be used as an alternative to a convolutional layer. The perturbation layer does away with convolution in the traditional sense and instead computes its response as a weighted linear combination of non-linearly activated additive noise perturbed inputs."
The patent was filed on April 29, 2019, under Application No. 1...