US Patent Issued to Smart Engines Service on July 28 for "Almost-indirect convolution in quantized neural networks" (Russian Inventors)

ALEXANDRIA, Va., July 28 -- United States Patent no. 12,694,262, issued on July 28, was assigned to Smart Engines Service LLC (Moscow).

"Almost-indirect convolution in quantized neural networks" was invented by Anton Vsevolodovich Trusov (Moscow), Elena Evgenyevna Limonova (Moscow) and Sergey Aleksandrovich Usilin (Moscow).

According to the abstract* released by the U.S. Patent & Trademark Office: "Almost-indirect convolution in quantized neural networks (QNNs). In an embodiment, an indirection buffer is allocated and initialized with pointers to block of values in an input tensor representing an input image. In one or more layers of a QNN, matrix multiplication of a left matrix by a right matrix is performed over a plurality of iteration...