ALEXANDRIA, Va., March 19 -- United States Patent no. 12,254,398, issued on March 18, was assigned to Amazon Technologies Inc. (Seattle).
"Sparse machine learning acceleration" was invented by Kun Xu (Austin, Texas), Ron Diamant (Santa Clara, Calif.) and Patricio Kaplan (Palo Alto, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "To reduce the storage size of weight tensors and speed up loading of weight tensors from system memory, a compression technique can be employed to remove zero values from a weight tensor before storing the weight tensor in system memory. A sparsity threshold can be enforced to achieve a compression ratio target by forcing small weight values to zero during training. When the we...