知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

49 records (took 0.022 seconds)

    METHOD AND SYSTEM FOR LEARNING MODELS FOR A MIXTURE OF DOMAINS (MOD)
    41.
    发明公开
    METHOD AND SYSTEM FOR LEARNING MODELS FOR A MIXTURE OF DOMAINS (MOD) 审中-公开

    公开(公告)号：US20240152787A1

    公开(公告)日：2024-05-09

    申请号：US17981107

    申请日：2022-11-04

    Applicant: Hitachi, Ltd.

    Inventor： Mahbubul ALAM ,  Ahmed FARAHAT ,  Dipanjan GHOSH ,  Jana BACKHUS ,  Teresa GONZALEZ ,  Chetan GUPTA

    IPC: G06N5/04 ,  G06N20/00

    CPC classification number: G06N5/043 ,  G06N20/00

    Abstract: Example implementations described herein involve systems and methods for efficient learning for mixture of domains which can include applying a clustering technique to a set of data comprised of multiple domains to obtain an initial domain separation of the set of data into one or more clusters; training one or more experts associated with each of the one or more clusters based on the initial domain separation where each expert corresponds with one domain of the multiple domains; inputting all data points to the one or more experts for refining each of the one or more clusters using expert output probabilities; retraining the one or more experts based on the refined one or more clusters; and training a gating mechanism to route an input to an appropriate expert of the one or more experts based on the refined one or more clusters.

    SYSTEM FOR PREDICTIVE MAINTENANCE USING TRACE NORM GENERATIVE ADVERSARIAL NETWORKS
    45.
    发明申请
    SYSTEM FOR PREDICTIVE MAINTENANCE USING TRACE NORM GENERATIVE ADVERSARIAL NETWORKS 有权

    公开(公告)号：US20210279596A1

    公开(公告)日：2021-09-09

    申请号：US16812088

    申请日：2020-03-06

    Applicant: Hitachi, Ltd.

    Inventor： Shuai ZHENG ,  Chetan GUPTA

    IPC: G06N3/08 ,  G06Q10/00 ,  G06N3/04

    Abstract: Example implementations involve a system for a system and method for Predictive Maintenance using Trace Norm Generative Adversarial Networks. Such example implementations can involve providing generated sensor data and real sensor data to a first network and to a second network, the first network configured to enforce trace norm minimization of the second network, the second network configured to distinguish between the generated sensor data and the real sensor data, the first network involving a subset of layers from the second network, and the second network integrated into a generative adversarial network.

    DEEP LEARNING NETWORK ARCHITECTURE OPTIMIZATION FOR UNCERTAINTY ESTIMATION IN REGRESSION
    47.
    发明申请
    DEEP LEARNING NETWORK ARCHITECTURE OPTIMIZATION FOR UNCERTAINTY ESTIMATION IN REGRESSION 审中-公开

    公开(公告)号：US20180341876A1

    公开(公告)日：2018-11-29

    申请号：US15605023

    申请日：2017-05-25

    Applicant: HITACHI, LTD.

    Inventor： Dipanjan GHOSH ,  Kosta RISTOVSKI ,  Chetan GUPTA ,  Ahmed FARAHAT

    IPC: G06N99/00 ,  G06N5/04

    Abstract: Equipment uptime is getting increasingly important across different industries which seek for new ways of increasing equipment availability. Detecting faults in the system by condition based maintenance (CBM) is not enough, because at the time of fault occurrence, the spare parts might not available or the needed resources (maintainers) are busy. Therefore, prediction failures and estimation of remaining useful life can be necessary. Moreover, not only predictions but also uncertainty in the predictions is critical for decision making. Example implementations described herein are directed to tuning parameters of deep learning network architecture by developing a mechanism to optimize for accuracy and uncertainty simultaneously, thereby achieving better asset availability, maintenance planning and decision making.

Patent Agency Ranking