公开(公告)号：US20250103305A1

公开(公告)日：2025-03-27

申请号：US18538895

申请日：2023-12-13

Applicant: QUALCOMM Technologies, Inc.

Inventor： Natasha BUTT ,  Auke Joris WIGGERS ,  Corrado RAINONE ,  Blazej Jakub Manczak ,  Taco Sebastiaan Cohen

IPC: G06F8/35

Abstract: Systems and techniques are described for providing iterative policy-guided program synthesis. For example, a device may generate, based on a policy that receives input-output data of one or more tasks as input, a first set of programs, add the first set of programs and the input-output data to the training dataset to generate an updated training dataset, train the policy based on the first set of programs and the input-output data to generate an updated policy, identify, based on the updated policy, a second set of programs for second input-output data for a second set of tasks, add the second set of programs and second input-output data to the updated training dataset to generate a second updated training dataset; and train the updated policy based on the second set of programs and the second input-output data to generate a second updated policy.

公开(公告)号：US12056615B2

公开(公告)日：2024-08-06

申请号：US17030361

申请日：2020-09-23

Applicant: QUALCOMM Technologies, Inc.

Inventor： Berkay Kicanaoglu ,  Taco Sebastiaan Cohen ,  Pim De Haan

IPC: G06N3/082 ,  G06N3/045 ,  G06T3/10

CPC classification number: G06N3/082 ,  G06N3/045 ,  G06T3/10

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.

公开(公告)号：US12158922B2

公开(公告)日：2024-12-03

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: G06F17/10 ,  G06F17/14 ,  G06N3/08 ,  G06N7/01 ,  G06V10/426 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82

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.