中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

304 records (took 0.028 seconds)

    FEDERATED LEARNING IN A DISAGGREGATED RADIO ACCESS NETWORK
    72.
    发明公开
    FEDERATED LEARNING IN A DISAGGREGATED RADIO ACCESS NETWORK 审中-公开

    公开(公告)号：US20230297875A1

    公开(公告)日：2023-09-21

    申请号：US17696712

    申请日：2022-03-16

    Applicant: QUALCOMM Incorporated

    Inventor： Eren BALEVI ,  Taesang YOO ,  Rajeev KUMAR ,  Shankar KRISHNAN ,  Aziz GHOLMIEH ,  Xipeng ZHU

    IPC: G06N20/00 ,  G06K9/62 ,  H04W8/18

    CPC classification number: G06N20/00 ,  G06K9/6256 ,  H04W8/18 ,  H04W88/085

    Abstract: Disclosed are systems and techniques for wireless communications. For instance, a network entity can determine a first data heterogeneity level associated with input data for training a machine learning model. In some cases, the network entity can determine, based on the first data heterogeneity level, a first data aggregation period for training the machine learning model. In some aspects, the network entity may obtain a first set of updated model parameters from a first client device and a second set of updated model parameters from a second client device, wherein the first set of updated model parameters and the second set of updated model parameters are based on the first data aggregation period. In some examples, the network entity can combine the first set of updated model parameters and the second set of updated model parameters to yield a first combined set of updated model parameters.

    MULTI-HEAD MACHINE LEARNING MODEL FOR ESTIMATING A PLURALITY OF PARAMETER VALUES
    74.
    发明公开
    MULTI-HEAD MACHINE LEARNING MODEL FOR ESTIMATING A PLURALITY OF PARAMETER VALUES 审中-公开

    公开(公告)号：US20230276480A1

    公开(公告)日：2023-08-31

    申请号：US17652854

    申请日：2022-02-28

    Applicant: QUALCOMM Incorporated

    Inventor： Mohamed Fouad Ahmed MARZBAN ,  Wooseok NAM ,  Tao LUO ,  Taesang YOO

    IPC: H04W72/08 ,  G06N3/08

    CPC classification number: H04W72/08 ,  G06N3/08

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first network node may receive a signal associated with a set of resources. The first network node may determine, using a multi-head machine learning model having a body module and a plurality of head modules, a plurality of estimated parameter values of a plurality of parameters corresponding to the set of resources, wherein the body module extracts a set of common features based at least in part on a set of model inputs corresponding to the set of resources, and wherein the plurality of head modules generate the plurality of estimated parameter values based at least in part on the set of common features. The first network node may perform a wireless communication operation based at least in part on the plurality of estimated parameter values. Numerous other aspects are described.

    GRADIENT DROPPING FOR FEDERATED LEARNING
    77.
    发明公开
    GRADIENT DROPPING FOR FEDERATED LEARNING 审中-公开

    公开(公告)号：US20230231640A1

    公开(公告)日：2023-07-20

    申请号：US17648113

    申请日：2022-01-14

    Applicant: QUALCOMM Incorporated

    Inventor： Eren BALEVI ,  Taesang YOO ,  Tao LUO ,  Hamed PEZESHKI

    IPC: H04B17/391 ,  H04B17/13 ,  H04B7/0417 ,  H04B7/0426

    CPC classification number: H04B17/391 ,  H04B7/0417 ,  H04B7/0426 ,  H04B17/13 ,  H04L27/2614

    Abstract: A UE may identify a plurality of local model update elements associated with an updated local machine learning model. The updated local machine learning model may have been generated based on a global machine learning model received from a base station and a local dataset. The UE may identify one or more local model update elements of the plurality of local model update elements for update element dropping based on at least one of a channel gain, a PAPR specification, an RF emission specification, or an RF condition. The UE may transmit, to the base station over a multiple access channel via analog signaling, at least some local model update elements of the plurality of local model update elements based on dropping of the identified one or more local model update elements.

    DATA GATHERING AND DATA SELECTION TO TRAIN A MACHINE LEARNING ALGORITHM
    78.
    发明申请
    DATA GATHERING AND DATA SELECTION TO TRAIN A MACHINE LEARNING ALGORITHM 有权

    公开(公告)号：US20230037704A1

    公开(公告)日：2023-02-09

    申请号：US17396417

    申请日：2021-08-06

    Applicant: QUALCOMM Incorporated

    Inventor： Mohammed HIRZALLAH ,  Srinivas YERRAMALLI ,  Taesang YOO ,  Rajat PRAKASH ,  Xiaoxia ZHANG

    IPC: H04W64/00 ,  H04W72/04 ,  G06K9/62

    Abstract: Disclosed are techniques for training a position estimation module. In an aspect, a first network entity obtains a plurality of positioning measurements, obtains a plurality of positions of one or more user equipments (UEs), the plurality of positions determined based on the plurality of positioning measurements, stores the plurality of positioning measurements as a plurality of features and the plurality of positions as a plurality of labels corresponding to the plurality of features, and trains the position estimation module with the plurality of features and the plurality of labels to determine a position of a UE from positioning measurements taken by the UE.

    SIGNALING FOR ADDITIONAL TRAINING OF NEURAL NETWORKS FOR MULTIPLE CHANNEL CONDITIONS
    79.
    发明申请
    SIGNALING FOR ADDITIONAL TRAINING OF NEURAL NETWORKS FOR MULTIPLE CHANNEL CONDITIONS 有权

    公开(公告)号：US20230021835A1

    公开(公告)日：2023-01-26

    申请号：US17385659

    申请日：2021-07-26

    Applicant: QUALCOMM Incorporated

    Inventor： Pavan Kumar VITTHALADEVUNI ,  Taesang YOO ,  Naga BHUSHAN

    IPC: H04L25/02 ,  H04B17/336 ,  G06N3/08 ,  G06N3/04

    Abstract: A method of wireless communication by a user equipment (UE) includes receiving, from a base station, a configuration to train a neural network for multiple different signal to noise ratios (SNRs) of a channel estimate for a wireless communication channel. The method also includes determining a current SNR of the channel estimate is above a first threshold value. The method further includes training the neural network based on the channel estimate, to obtain a first trained neural network. The method still further includes perturbing the channel estimate to obtain a perturbed channel estimate, and training the neural network based on the perturbed channel estimate, to obtain a second trained neural network. The method includes reporting, to the base station, parameters of the first trained neural network along with the channel estimate, and parameters of the second trained neural network.

Patent Agency Ranking