US Patent Issued to Black Sesame Technologies on Sept. 30 for "Heterogeneous architecture for depthwise-seperable convolution based neural network computation acceleration" (California Inventors)

ALEXANDRIA, Va., Sept. 30 -- United States Patent no. 12,430,544, issued on Sept. 30, was assigned to Black Sesame Technologies Inc. (San Jose, Calif.).

"Heterogeneous architecture for depthwise-seperable convolution based neural network computation acceleration" was invented by Yi Wang (San Jose, Calif.) and Zheng Qi (Cupertino, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present invention relates to a method and a system for performing depthwise separable convolution on an input data in a convolutional neural network. The invention utilizes a heterogeneous architecture with a number of MAC arrays including 1D MAC arrays and 2D MAC arrays with a Winograd conversion logic to perform depthwise s...