US Patent Issued to SRI International on April 14 for "Progressive neural ordinary differential equations" (New Jersey, California Inventors)

ALEXANDRIA, Va., April 15 -- United States Patent no. 12,602,448, issued on April 14, was assigned to SRI International (Menlo Park, Calif.).

"Progressive neural ordinary differential equations" was invented by Yi Yao (Princeton, N.J.), Ajay Divakaran (Monmouth Junction, N.J.) and Hammad A. Ayyubi (La Jolla, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques are described for neural networks based on Progressive Neural ODEs (PODEs). In an example, a method to progressively train a neural ordinary differential equation (NODE) model comprises processing, by a machine learning system executed by a computing system, first training data, the first training data having a first complexity, to perform ...