Qualcomm Incorporated

Qualcomm Technologies, Inc.

Pim De Haan

Taco Sebastiaan Cohen

Max Welling

Berkay Kicanaoglu

Maurice Weiler

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.

Gauge equivariant geometric graph convolutional neural network

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.

Growing community of inventors

Amsterdam, Netherlands

Pim De Haan