US Patent Issued to Microsoft Technology Licensing on Sept. 23 for "Selecting a neural network architecture for a supervised machine learning problem" (Washington, Massachusetts Inventors)

ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,581, issued on Sept. 23, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Selecting a neural network architecture for a supervised machine learning problem" was invented by Saeed Amizadeh (Seattle), Ge Yang (Bellevue, Wash.), Nicolo Fusi (Watertown, Mass.) and Francesco Paolo Casale (Boston).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods, for selecting a neural network for a machine learning (ML) problem, are disclosed. A method includes accessing an input matrix, and accessing an ML problem space associated with an ML problem and multiple untrained candidate neural networks for solving the ML problem. The me...