中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.026 seconds)

    FEDERATED LEARNING
    1.
    发明公开
    FEDERATED LEARNING 审中-公开

    公开(公告)号：US20230351245A1

    公开(公告)日：2023-11-02

    申请号：US17734510

    申请日：2022-05-02

    Applicant: Nokia Technologies Oy

    Inventor： Tejas SUBRAMANYA ,  Saurabh KHARE ,  Chaitanya AGGARWAL

    IPC: G06N20/00 ,  H04W4/20

    CPC classification number: G06N20/00 ,  H04W4/20

    Abstract: According to an example aspect of the present invention, there is provided an apparatus configured to obtain reliability values for each user equipment in a group of user equipments, obtain, for each user equipment in the group, a reliability value for a training data set stored in the user equipment, each user equipment storing a distinct training data set, and direct a subset of the group of user equipments to separately perform a machine learning training process in the user equipments in the subset, wherein the apparatus is configured to select the subset based on the reliability values for the user equipments and the reliability values for the training data sets.

    TRUST RELATED MANAGEMENT OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING PIPELINES IN RELATION TO ADVERSARIAL ROBUSTNESS
    2.
    发明申请
    TRUST RELATED MANAGEMENT OF ARTIFICIAL INTELLIGENCE OR MACHINE LEARNING PIPELINES IN RELATION TO ADVERSARIAL ROBUSTNESS 有权

    公开(公告)号：US20250036960A1

    公开(公告)日：2025-01-30

    申请号：US18706976

    申请日：2021-11-09

    Applicant: Nokia Technologies Oy

    Inventor： Tejas SUBRAMANYA ,  Janne ALI-TOLPPA

    IPC: G06N3/094 ,  G06F21/55

    Abstract: There are provided measures for trust related management of artificial intelligence or machine learning pipelines in relation to adversarial robustness. Such measures exemplarily comprise, at a first network entity managing artificial intelligence or machine learning trustworthiness in a network, transmitting a first artificial intelligence or machine learning trustworthiness related message towards a second network entity managing artificial intelligence or machine learning trustworthiness in an artificial intelligence or machine learning pipeline in said network, and receiving a second artificial intelligence or machine learning trustworthiness related message from said second network entity, wherein said first artificial intelligence or machine learning trustworthiness related message is related to artificial intelligence or machine learning model adversarial robustness as a trustworthiness sub-factor, said second artificial intelligence or machine learning trustworthiness related message is related to artificial intelligence or machine learning model adversarial robustness as said trustworthiness sub-factor, and said first artificial intelligence or machine learning trustworthiness related message comprises a first information element including at least one first artificial intelligence or machine learning model adversarial robustness related parameter.

    APPARATUS, METHOD, AND COMPUTER PROGRAM
    3.
    发明公开
    APPARATUS, METHOD, AND COMPUTER PROGRAM 审中-公开

    公开(公告)号：US20240333603A1

    公开(公告)日：2024-10-03

    申请号：US18575407

    申请日：2021-06-30

    Applicant: Nokia Technologies Oy

    Inventor： Prajwal KESHAVAMURTHY ,  Tejas SUBRAMANYA ,  Gerald KUNZMANN

    IPC: H04L41/16 ,  H04L43/0882

    CPC classification number: H04L41/16 ,  H04L43/0882

    Abstract: The disclosure relates to an apparatus comprising at least one processor and at least one memory including computer code for one or more programs, the at least one memory and the computer code configured, with the at least one processor, to cause the apparatus at least to: determine (700) whether at least one reporting criterion is met; and trigger (702) the provision of a report to a central node when the at least one reporting criterion is met, wherein the report comprises an indication that at least one reporting criterion is met and/or an indication of the at least one reporting criterion being met.

    APPARATUS, METHOD AND COMPUTER PROGRAM
    5.
    发明公开
    APPARATUS, METHOD AND COMPUTER PROGRAM 审中-公开

    公开(公告)号：US20240275690A1

    公开(公告)日：2024-08-15

    申请号：US18432149

    申请日：2024-02-05

    Applicant: Nokia Technologies Oy

    Inventor： Tejas SUBRAMANYA ,  Sina KHATIBI ,  Fabio GIUST

    IPC: H04L41/16 ,  G06N20/00

    CPC classification number: H04L41/16 ,  G06N20/00

    Abstract: There is provided an apparatus means for, at a central node associated with a plurality of distributed nodes, determining that at least one distributed node of the plurality of distributed nodes has not provided training information relating to a training process of a machine learning model before expiry of a first timer for a given iteration of N iterations of the training process, means for generating analytic information relative to the at least one distributed node, wherein the analytic information comprises a count based on the determining and means for providing the analytic information to a storage function.

    PROVIDING CONFIDENCE THRESHOLDS IN AN ANALYTICS REQUEST OR SUBSCRIPTION
    6.
    发明公开
    PROVIDING CONFIDENCE THRESHOLDS IN AN ANALYTICS REQUEST OR SUBSCRIPTION 审中-公开

    公开(公告)号：US20240214293A1

    公开(公告)日：2024-06-27

    申请号：US18273822

    申请日：2021-02-15

    Applicant: NOKIA TECHNOLOGIES OY

    Inventor： Tejas SUBRAMANYA ,  Janne Tapio ALI-TOLPPA ,  Márton KAJÓ

    IPC: H04L43/16 ,  H04L41/5019

    CPC classification number: H04L43/16 ,  H04L41/5019

    Abstract: Certain example embodiments provide systems, methods, apparatuses, and computer program products for providing confidence thresholds in an analytics request or subscription. For example, certain embodiments may include a confidence threshold for each reporting threshold (e.g., quality of service (QoS) metric-specific reporting threshold) in an analytics request or subscription (e.g., a network data analytics function (NWDAF) QoS sustainability analytics request or subscription). The confidence threshold (lower bound) can be determined by the consumer application based on their individual needs, e.g., based on the cost or impact of the compensating actions on the predicted QoS sustainability notification. The confidence threshold, in combination with the reporting threshold, may define the conditions for analytics events and/or notifications (e.g., QOS sustainability prediction analytics events and the related notifications).

    ABNORMAL MODEL BEHAVIOR DETECTION
    7.
    发明公开
    ABNORMAL MODEL BEHAVIOR DETECTION 审中-公开

    公开(公告)号：US20240046153A1

    公开(公告)日：2024-02-08

    申请号：US18364864

    申请日：2023-08-03

    Applicant: Nokia Technologies Oy

    Inventor： Chaitanya AGGARWAL ,  Saurabh KHARE ,  Tejas SUBRAMANYA

    IPC: G06N20/00 ,  H04L41/14 ,  H04L41/16

    CPC classification number: G06N20/00 ,  H04L41/145 ,  H04L41/16

    Abstract: Example embodiments of the present disclosure relate to abnormal model behavior detection. A first apparatus obtains a machine learning model and expected behavior information of the machine learning model. The first apparatus monitors behavior information of the machine learning model during execution of the machine learning model; and determines occurrence of an abnormal behavior of the machine learning model during the execution by comparing the monitored behavior information with the expected behavior information.

Patent Agency Ranking