中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.019 seconds)

    METHOD AND SYSTEM FOR FEDERATED LEARNING
    12.
    发明公开
    METHOD AND SYSTEM FOR FEDERATED LEARNING 审中-公开

    公开(公告)号：US20240135194A1

    公开(公告)日：2024-04-25

    申请号：US18512195

    申请日：2023-11-17

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Minyoung KIM ,  Timothy HOSPEDALES

    IPC: G06N3/098

    CPC classification number: G06N3/098

    Abstract: Broadly speaking, embodiments of the present techniques provide a method for training a machine learning, ML, model to update global and local versions of a model. We propose a novel hierarchical Bayesian approach to Federated Learning (FL), where our models reasonably describe the generative process of clients' local data via hierarchical Bayesian modeling: constituting random variables of local models for clients that are governed by a higher-level global variate. Interestingly, the variational inference in our Bayesian model leads to an optimisation problem whose block-coordinate descent solution becomes a distributed algorithm that is separable over clients and allows them not to reveal their own private data at all, thus fully compatible with FL.

    METHOD AND APPARATUS FOR CONCEPT MATCHING
    13.
    发明申请
    METHOD AND APPARATUS FOR CONCEPT MATCHING 有权

    公开(公告)号：US20230137671A1

    公开(公告)日：2023-05-04

    申请号：US17434314

    申请日：2021-08-20

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Vladimir PAVLOVIC ,  Minyoung KIM ,  Ricardo GUERRERO ,  Hai Xuan PHAM

    IPC: G06F16/9535 ,  G06F16/9538 ,  G06F3/0482 ,  G06F18/22 ,  G06N3/08

    Abstract: A computer-implemented method for concept matching using a machine learning model, may include: receiving, from a user, a search query comprising: at least one criterion that represents at least one concept; inputting the received at least our criterion into at least one neural network for processing the search query; determining, using the at least one neural network, the at least one concept represented by the at least one criterion; retrieving, from a storage, at least one data item winch matches the determined at least one concept, through a cross-modal data retrieval method of retrieving a data type different from an input data type; and outputting the retrieved at least one data item in response to the search query.

    METHOD AND APPARATUS FOR META FEW-SHOT LEARNER
    14.
    发明申请
    METHOD AND APPARATUS FOR META FEW-SHOT LEARNER 有权

    公开(公告)号：US20230117307A1

    公开(公告)日：2023-04-20

    申请号：US17843590

    申请日：2022-06-17

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Minyoung KIM ,  Timothy HOSPEDALES

    IPC: G06V10/776 ,  G06V10/82 ,  G06V10/70 ,  G06V10/774

    Abstract: The subject-matter of the present disclosure relates to a computer-implemented method of training a machine learning, ML, meta learner classifier model to perform few-shot image or speech classification, the method comprising: training the machine learning, ML, meta learner classifier model by: iteratively obtaining a support set and a query set of a current episode; adapting the model using the support set; measuring a performance of the adapted model using the query set; and updating the classifier based on the performance; wherein adapting the model using the support set comprises: deriving a Laplace approximated posterior using a linear classifier based on Gaussian mixture fitting; and deriving a predictive distribution using the approximated posterior; wherein measuring the performance of the adapted model using the query set comprises: determining a loss associated with the predictive distribution using the query set; and wherein updating the classifier based on the performance comprises minimising the loss.

Patent Agency Ranking