US Patent Issued to Red Hat on Jan. 20 for "Efficient execution of group-sparsified neural networks" (Massachusetts Inventors)

ALEXANDRIA, Va., Jan. 20 -- United States Patent no. 12,530,573, issued on Jan. 20, was assigned to Red Hat Inc. (Raleigh, N.C.).

"Efficient execution of group-sparsified neural networks" was invented by Alexander Matveev (Cambridge, Mass.) and Nir Shavit (Cambridge, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Creating neural network (NN) code may include for each row in a kernel matrix, finding the first non-zero element; and creating a loop including multiply and add instructions. On each iteration of the loop, the multiply and add instructions may be executed, and the position of the kernel matrix operand operated on by each multiply and add may be correlated to the loop iteration number. Instruc...