知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.057 seconds)

    SPARSITY-INDUCING FEDERATED MACHINE LEARNING
    3.
    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.

    MULTI-OBJECT POSITIONING USING MIXTURE DENSITY NETWORKS
    5.
    发明申请
    MULTI-OBJECT POSITIONING USING MIXTURE DENSITY NETWORKS 有权

    公开(公告)号：US20220272489A1

    公开(公告)日：2022-08-25

    申请号：US17182153

    申请日：2021-02-22

    Applicant: QUALCOMM Incorporated

    Inventor： Farhad GHAZVINIAN ZANJANI ,  Arash BEHBOODI ,  Daniel Hendricus Franciscus DIJKMAN ,  Ilia KARMANOV ,  Simone MERLIN ,  Max WELLING

    IPC: H04W4/029

    Abstract: Certain aspects of the present disclosure provide techniques for object positioning using mixture density networks, comprising: receiving radio frequency (RF) signal data collected in a physical space; generating a feature vector encoding the RF signal data by processing the RF signal data using a first neural network; processing the feature vector using a first mixture model to generate a first encoding tensor indicating a set of moving objects in the physical space, a first location tensor indicating a location of each of the moving objects in the physical space, and a first uncertainty tensor indicating uncertainty of the locations of each of the moving objects in the physical space; and outputting at least one location from the first location tensor.

    TEMPORAL DIFFERENCE ESTIMATION IN AN ARTIFICIAL NEURAL NETWORK
    6.
    发明申请
    TEMPORAL DIFFERENCE ESTIMATION IN AN ARTIFICIAL NEURAL NETWORK 审中-公开

    公开(公告)号：US20180121791A1

    公开(公告)日：2018-05-03

    申请号：US15590609

    申请日：2017-05-09

    Applicant: QUALCOMM Incorporated

    Inventor： Peter O'CONNOR ,  Max WELLING

    IPC: G06N3/04

    CPC classification number: G06N3/049

    Abstract: A method of computation in a deep neural network includes discretizing input signals and computing a temporal difference of the discrete input signals to produce a discretized temporal difference. The method also includes applying weights of a first layer of the deep neural network to the discretized temporal difference to create an output of a weight matrix. The output of the weight matrix is temporally summed with a previous output of the weight matrix. An activation function is applied to the temporally summed output to create a next input signal to a next layer of the deep neural network.

    HYPERNETWORK KALMAN FILTER FOR CHANNEL ESTIMATION AND TRACKING
    7.
    发明申请
    HYPERNETWORK KALMAN FILTER FOR CHANNEL ESTIMATION AND TRACKING 有权

    公开(公告)号：US20220376801A1

    公开(公告)日：2022-11-24

    申请号：US17734524

    申请日：2022-05-02

    Applicant: QUALCOMM Incorporated

    Inventor： Kumar PRATIK ,  Arash BEHBOODI ,  Joseph Binamira SORIAGA ,  Max WELLING

    IPC: H04B17/373 ,  H04B17/391

    Abstract: A processor-implemented method is presented. The method includes receiving an input sequence comprising a group of channel dynamics observations for a wireless communication channel. Each channel dynamics observation may correspond to a timing of a group of timings. The method also includes determining, via a recurrent neural network (RNN), a residual at each of the group of timings based on the group of channel dynamics observations. The method further includes updating Kalman filter (KF) parameters based on the residual and estimating, via the KF, a channel state based on the updated KF parameters.

    QUANTUM INSPIRED CONVOLUTIONAL KERNELS FOR CONVOLUTIONAL NEURAL NETWORKS
    9.
    发明申请
    QUANTUM INSPIRED CONVOLUTIONAL KERNELS FOR CONVOLUTIONAL NEURAL NETWORKS 有权

    公开(公告)号：US20210089955A1

    公开(公告)日：2021-03-25

    申请号：US17031501

    申请日：2020-09-24

    Applicant: QUALCOMM Incorporated

    Inventor： Roberto BONDESAN ,  Max WELLING

    IPC: G06N10/00 ,  G06N3/04 ,  G06N3/063 ,  G06N7/00 ,  G06N5/04 ,  G06F17/16

    Abstract: Certain aspects of the present disclosure provide a method for performing quantum convolution, including: receiving input data at a neural network model, wherein the neural network model comprises at least one quantum convolutional layer; performing quantum convolution on the input data using the at least one quantum convolutional layer; generating an output wave function based on the quantum convolution using the at least one quantum convolution layer; generating a marginal probability distribution based on the output wave function; and generating an inference based on the marginal probability distribution.

    Channel Gating For Conditional Computation
    10.
    发明公开
    Channel Gating For Conditional Computation 审中-公开

    公开(公告)号：US20230334324A1

    公开(公告)日：2023-10-19

    申请号：US18337462

    申请日：2023-06-20

    Applicant: QUALCOMM Incorporated

    Inventor： Babak EHTESHAMI BEJNORDI ,  Tijmen Pieter Frederik BLANKEVOORT ,  Max WELLING

    IPC: G06N3/08 ,  G06N20/00

    CPC classification number: G06N3/084 ,  G06N20/00

    Abstract: A computing device may be configured to intelligently activate gating within a current layer of a neural network that includes two or more filters. The computing device may receive a layer-specific input data that is specific to the current layer of the neural network, generate statistics based on the received layer-specific input data; and use the generated statistics to assign a relevance score to each of the two or more filters. Each assigned relevance score may indicate the relevance of the corresponding filter to the received layer-specific input data. The computing device may determine an activation status of each of the two or more filters in the current layer based on the identified relevance and apply the received layer-specific input data to the activated filters in the two or more filters to generate an output activation for the current layer of the neural network.

Patent Agency Ranking