US Patent Issued on May 6 for "Sparse local connected artificial neural network architectures involving hybrid local/nonlocal structure" (Mississippi Inventor)

ALEXANDRIA, Va., June 10 -- United States Patent no. 12,293,290, issued on May 6.

"Sparse local connected artificial neural network architectures involving hybrid local/nonlocal structure" was invented by Benjamin Forrest Dribus (Hattiesburg, Miss.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present invention in a first embodiment is a method of constructing a geometry-induced sparse local connected network architecture, the method comprising: choosing a geometry, choosing a direction of data flow in the geometry, choosing a node set as a finite subset of the geometry, choosing local edges between each node and nodes in preceding layers with respect to the geometry and direction of data flow, and choo...