ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,525,009, issued on Jan. 13, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Pruning a vision transformer" was invented by Hongxu Yin (San Jose, Calif.), Huanrui Yang (Durham, N.C.), Pavlo Molchanov (San Jose, Calif.) and Jan Kautz (Lexington, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A vision transformer is a deep learning model used to perform vision processing tasks such as image recognition. Vision transformers are currently designed with a plurality of same-size blocks that perform the vision processing tasks. However, some portions of these blocks are unnecessary and not only slow down the vision transformer but use more memory than...