US Patent Issued on July 7 for "Sparsity for neural network models based on sparsity attributes" (Chinese Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,696, issued on July 7.

"Sparsity for neural network models based on sparsity attributes" was invented by Ningxin Zheng (Shanghai), Quanlu Zhang (Beijing), Yuqing Yang (Shanghai), Lingxiao Ma (Beijing), Fan Yang (Beijing), Yang Wang (Beijing), Mao Yang (Beijing) and Lidong Zhou (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments of the present disclosure include systems and methods for providing sparsity for neural network models based on sparsity attributes. A first neural network model definition is received. The first neural network model definition specifies a neural network model comprising a set of tensors and a set of sparsity a...