ALEXANDRIA, Va., Sept. 10 -- United States Patent no. 12,412,085, issued on Sept. 9, was assigned to QUALCOMM Inc. (San Diego).
"Data and compute efficient equivariant convolutional networks" was invented by Mirgahney Husham Awadelkareem Mohamed (Amsterdam), Gabriele Cesa (Diemen, Netherlands), Taco Sebastiaan Cohen (Amsterdam) and Max Welling (Bussum, Netherlands).
According to the abstract* released by the U.S. Patent & Trademark Office: "Certain aspects of the present disclosure provide a method of performing machine learning, comprising: generating a neural network model; and training the neural network model for a task with a first set of input data, wherein: the training uses a total loss function total including an equivariance los...