中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.019 seconds)

    METHOD AND APPARATUS FOR GENERATING A NOISE-RESILIENT MACHINE LEARNING MODEL
    1.
    发明公开
    METHOD AND APPARATUS FOR GENERATING A NOISE-RESILIENT MACHINE LEARNING MODEL 审中-公开

    公开(公告)号：US20240330685A1

    公开(公告)日：2024-10-03

    申请号：US18742494

    申请日：2024-06-13

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Minyoung KIM ,  Timothy HOSPEDALES ,  Da LI ,  Xu HU

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: The present application relates to a computer-implemented method for an improved technique for optimising the loss function during deep learning. The method includes receiving a training data set comprising a plurality of data items, initialising weights of at least one neural network layer of the ML model, and training, using an iterative process, the at least one neural network layer of the ML model by inputting, into the at least one neural network layer, the plurality of data items, processing the plurality of data items using the at least one neural network layer and the weights, optimising a loss function of the weights by simultaneously minimising a loss value and a loss sharpness using weights that lie in a neighbourhood having a similar low loss value, wherein the neighbourhood is determined by a geometry of a parameter space defined by the weights of the ML model, and updating the weights of the at least one neural network layer using the optimised loss function.

    METHOD AND SYSTEM FOR FEDERATED LEARNING
    3.
    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 META FEW-SHOT LEARNER
    4.
    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.

    METHOD AND APPARATUS FOR SEMI-SUPERVISED LEARNING
    6.
    发明公开
    METHOD AND APPARATUS FOR SEMI-SUPERVISED LEARNING 审中-公开

    公开(公告)号：US20230177344A1

    公开(公告)日：2023-06-08

    申请号：US17436927

    申请日：2021-05-25

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Ivana BALAZEVIC ,  Carl ALLEN ,  Timothy HOSPEDALES

    IPC: G06N3/088 ,  G06V10/774 ,  G06V10/82

    CPC classification number: G06N3/088 ,  G06V10/7753 ,  G06V10/82

    Abstract: Provided is a computer-implemented method for training a machine learning (ML) model using labelled and unlabelled data, the method comprising obtaining a set or training data comprising a set of labelled data items and a set of unlabelled data items, training a loss module of the ML model using labels in the set of labelled data items, to generate a trained loss module capable of estimating a likelihood of a label for a data item, and training a task module of the ML model using the loss module, the set of labelled data items, and the set of unlabelled data items, to generate a trained task module capable of making a prediction of a label for input data.

Patent Agency Ranking