US Patent Issued on Nov. 18 for "Device and computer implemented method for training an artificial neural network using channel groups" (Dutch, German Inventors)

ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,364, issued on Nov. 18.

"Device and computer implemented method for training an artificial neural network using channel groups" was invented by Thomas Andy Keller (Amsterdam), Anna Khoreva (Stuttgart, Germany) and Max Welling (Bussum, Netherlands).

According to the abstract* released by the U.S. Patent & Trademark Office: "Device and method for training an artificial neural network, including providing a neural network layer for an equivariant feature mapping having a plurality of output channels, grouping channels of the output channels into a number of distinct groups, wherein the output channels of each individual distinct group are organized into an individual grid defining a...