知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.013 seconds)

    EFFICIENT MACHINE LEARNING MODEL ARCHITECTURES FOR TRAINING AND INFERENCE
    1.
    发明公开
    EFFICIENT MACHINE LEARNING MODEL ARCHITECTURES FOR TRAINING AND INFERENCE 审中-公开

    公开(公告)号：US20240202529A1

    公开(公告)日：2024-06-20

    申请号：US18068987

    申请日：2022-12-20

    Applicant: QUALCOMM Incorporated

    Inventor： Joseph Binamira SORIAGA ,  Hossein HOSSEINI

    IPC: G06N3/084

    CPC classification number: G06N3/084

    Abstract: Certain aspects of the present disclosure provide techniques for improved machine learning. A data tensor is generated as output from a layer of a neural network. A first subset of the first data tensor and a second subset of the first data tensor are generated using a tensor splitting operation. The second subset of the first data tensor is stored, and the first subset of the first data tensor is provided to a subsequent layer of the neural network. One or more parameters of the layer of the neural network are refined based at least in part on the stored second subset of the first data tensor.

    FEDERATED LEARNING USING SECURE CENTERS OF CLIENT DEVICE EMBEDDINGS
    4.
    发明申请
    FEDERATED LEARNING USING SECURE CENTERS OF CLIENT DEVICE EMBEDDINGS 有权

    公开(公告)号：US20220383197A1

    公开(公告)日：2022-12-01

    申请号：US17828613

    申请日：2022-05-31

    Applicant: QUALCOMM Incorporated

    Inventor： Hyunsin PARK ,  Hossein HOSSEINI ,  Sungrack YUN ,  Kyu Woong HWANG

    IPC: G06N20/00 ,  G06F21/62

    Abstract: Certain aspects of the present disclosure provide techniques for training a machine learning model. The method generally includes receiving, at a local device from a server, information defining a global version of a machine learning model. A local version of the machine learning model and a local center associated with the local version of the machine learning model are generated based on embeddings generated from local data at a client device and the global version of the machine learning model. A secure center different from the local center is generated based, at least in part, on information about secure centers shared by a plurality of other devices participating in a federated learning scheme. Information about the local version of the machine learning model and information about the secure center is transmitted by the local device to the server.

    SPARSITY-INDUCING FEDERATED MACHINE LEARNING
    5.
    发明公开
    SPARSITY-INDUCING FEDERATED MACHINE LEARNING 审中-公开

    公开(公告)号：US20230169350A1

    公开(公告)日：2023-06-01

    申请号：US18040111

    申请日：2021-09-28

    Applicant: QUALCOMM Incorporated

    Inventor： Christos LOUIZOS ,  Hossein HOSSEINI ,  Matthias REISSER ,  Max WELLING ,  Joseph Binamira SORIAGA

    IPC: G06N3/098

    CPC classification number: G06N3/098

    Abstract: Aspects described herein provide techniques for performing federated learning of a machine learning model, comprising: for each respective client of a plurality of clients and for each training round in a plurality of training rounds: generating a subset of model elements for the respective client based on sampling a gate probability distribution for each model element of a set of model elements for a global machine learning model; transmitting to the respective client: the subset of model elements; and a set of gate probabilities based on the sampling, wherein each gate probability of the set of gate probabilities is associated with one model element of the subset of model elements; receiving from each respective client of the plurality of clients a respective set of model updates; and updating the global machine learning model based on the respective set of model updates from each respective client of the plurality of clients.

    PRIVACY-AWARE PRUNING IN MACHINE LEARNING
    6.
    发明申请
    PRIVACY-AWARE PRUNING IN MACHINE LEARNING 有权

    公开(公告)号：US20220318412A1

    公开(公告)日：2022-10-06

    申请号：US17223946

    申请日：2021-04-06

    Applicant: QUALCOMM Incorporated

    Inventor： Yunhui GUO ,  Hossein HOSSEINI ,  Christos LOUIZOS ,  Joseph Binamira SORIAGA

    IPC: G06F21/62 ,  G06N3/08 ,  G06F17/18

    Abstract: Certain aspects of the present disclosure provide techniques for improved machine learning using private variational dropout. A set of parameters of a global machine learning model is updated based on a local data set, and the set of parameters is pruned based on pruning criteria. A noise-augmented set of gradients is computed for a subset of parameters remaining after the pruning, based in part on a noise value, and the noise-augmented set of gradients is transmitted to a global model server.

Patent Agency Ranking