公开(公告)号：US20210034928A1

公开(公告)日：2021-02-04

申请号：US16945625

申请日：2020-07-31

Applicant: QUALCOMM Technologies, Inc.

Inventor： Changyong OH ,  Efstratios GAVVES ,  Jakub Mikolaj TOMCZAK ,  Max WELLING

IPC: G06K9/62 ,  G06N7/00

Abstract: Certain aspects provide a method for determining a solution to a combinatorial optimization problem, including: determining a plurality of subgraphs, wherein each subgraph of the plurality of subgraphs corresponds to a combinatorial variable of the plurality of combinatorial variables; determining a combinatorial graph based on the plurality of subgraphs; determining evaluation data comprising a set of vertices in the combinatorial graph and evaluations on the set of vertices; fitting a Gaussian process to the evaluation data; determining an acquisition function for vertices in the combinatorial graph using a predictive mean and a predictive variance from the fitted Gaussian process; optimizing the acquisition function on the combinatorial graph to determine a next vertex to evaluate; evaluating the next vertex; updating the evaluation data with a tuple of the next vertex and its evaluation; and determining a solution to the problem, wherein the solution comprises a vertex of the combinatorial graph.

公开(公告)号：US20230118025A1

公开(公告)日：2023-04-20

申请号：US17914297

申请日：2021-06-03

Applicant: QUALCOMM Technologies, Inc.

Inventor： Matthias REISSER ,  Max WELLING ,  Efstratios GAVVES ,  Christos LOUIZOS

IPC: G06N3/098 ,  G06N3/045

Abstract: A method of collaboratively training a neural network model, includes receiving a local update from a subset of the multiple users. The local update is related to one or more subsets of a dataset of the neural network model. A local component of the neural network model identifies a subset of the one or more subsets to which a data point belongs. A global update is computed for the neural network model based on the local updates from the subset of the users. The global updates for each portion of the network are aggregated to train the neural network model.

公开(公告)号：US20230036702A1

公开(公告)日：2023-02-02

申请号：US17756957

申请日：2020-12-14

Applicant: Qualcomm Technologies, Inc.

Inventor： Matthias REISSER ,  Max WELLING ,  Efstratios GAVVES ,  Christos LOUIZOS

IPC: G06N3/02

Abstract: Aspects described herein provide a method of processing data, including: receiving a set of global parameters for a plurality of machine learning models; processing data stored locally on an processing device with the plurality of machine learning models according to the set of global parameters to generate a machine learning model output; receiving, at the processing device, user feedback regarding machine learning model output for the plurality of machine learning models; performing an optimization of the plurality of machine learning models based on the machine learning output and the user feedback to generate locally updated machine learning model parameters; sending the locally updated machine learning model parameters to a remote processing device; and receiving a set of globally updated machine learning model parameters for the plurality of machine learning models.

公开(公告)号：US20240257411A1

公开(公告)日：2024-08-01

申请号：US18159622

申请日：2023-01-25

Applicant: QUALCOMM Technologies, Inc.

Inventor： Gabriele CESA ,  Arash BEHBOODI ,  Taco Sebastiaan COHEN ,  Max WELLING

IPC: G06T11/00 ,  G06T5/00 ,  G06T5/10 ,  G06T5/50 ,  G06T7/70

CPC classification number: G06T11/005 ,  G06T5/002 ,  G06T5/10 ,  G06T5/50 ,  G06T7/70 ,  G06T11/008 ,  G06T2207/10056 ,  G06T2207/20084 ,  G06T2207/30004

Abstract: Certain aspects of the present disclosure provide techniques for pose estimation for three-dimensional object reconstruction. In one example, a method, includes receiving image data, wherein the image data comprises a plurality of images taken from varying poses; identifying one or more pairs of spatially related images within the plurality of images; generating a synchronization graph indicative of at least one similarity metric between the plurality of images, based at least in part on the identified one of more pairs of spatially related images; and estimating a pose of an object depicted in the plurality of images based on the synchronization graph.

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.