QUALCOMM Incorporated
DATA AND COMPUTE EFFICIENT EQUIVARIANT CONVOLUTIONAL NETWORKS

Abstract:

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 .sub.total including an equivariance loss component .sub.equivarnace according to .sub.total=.sub.task+.alpha..sub.equivarnace, and .alpha.>0.