公开(公告)号：US20210248504A1

公开(公告)日：2021-08-12

申请号：US17169338

申请日：2021-02-05

Applicant: QUALCOMM TECHNOLOGIES, INC.

Inventor： Pim DE HAAN ,  Maurice WEILER ,  Taco Sebastiaan COHEN ,  Max WELLING

IPC: G06N7/00 ,  G06N3/08 ,  G06F17/14

Abstract: Certain aspects of the present disclosure provide a method for performing machine learning, comprising: determining a plurality of vertices in a neighborhood associated with a mesh including a target vertex; determining a linear transformation configured to parallel transport signals along all edges in the mesh to the target vertex; applying the linear transformation to the plurality of vertices in the neighborhood to form a combined signal at the target vertex; determining a set of basis filters; linearly combining the basis filters using a set of learned parameters to form a gauge equivariant convolution filter, wherein the gauge equivariant convolution filter is constrained to maintain gauge equivariance; applying the gauge equivariant convolution filter to the combined signal to form an intermediate output; and applying a nonlinearity to the intermediate output to form a convolution output.

公开(公告)号：US20210089923A1

公开(公告)日：2021-03-25

申请号：US17030361

申请日：2020-09-23

Applicant: QUALCOMM Technologies, Inc.

Inventor： Berkay KICANAOGLU ,  Taco Sebastiaan COHEN ,  Pim DE HAAN

IPC: G06N3/08 ,  G06N3/04 ,  G06T3/00

Abstract: A method for generating a convolutional neural network to operate on a spherical manifold, generates locally-defined gauges at multiple positions on the spherical manifold. A convolution is defined at each of the positions on the spherical manifold with respect to an arbitrarily selected locally-defined gauge. The results of the convolution that is defined at each position based on gauge equivariance is translated to obtain a manifold convolution.