中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

27 records (took 0.052 seconds)

    MITIGATING THE INFLUENCE OF BIASED TRAINING INSTANCES WITHOUT REFITTING
    1.
    发明公开
    MITIGATING THE INFLUENCE OF BIASED TRAINING INSTANCES WITHOUT REFITTING 审中-公开

    公开(公告)号：US20240135238A1

    公开(公告)日：2024-04-25

    申请号：US18045253

    申请日：2022-10-10

    Applicant: International Business Machines Corporation

    Inventor： Prasanna Sattigeri ,  Soumya Ghosh ,  Inkit Padhi ,  Pierre L. Dognin ,  Kush Raj Varshney

    IPC: G06N20/00 ,  G06F17/16

    CPC classification number: G06N20/00 ,  G06F17/16

    Abstract: One or more systems, devices, computer program products and/or computer implemented methods of use provided herein relate to a process of mitigating biased training instances associated with a machine learning model without additional refitting of the machine learning model. A system can comprise a memory that stores computer executable components, and a processor that executed the computer executable components stored in the memory, wherein the computer executable components can comprise a training data influence estimation component and an influence mitigation component. The training data influence estimation component can receive a pre-trained machine learning model and calculate a fairness influence score of training instances on group fairness metrics associated with the pre-trained machine learning model. The influence mitigation component can perform post-hoc unfairness mitigation by removing the effect of at least one training instance based on the fairness influence score to mitigate biased training instances without refitting the pre-trained machine learning model.

    AUTOMATICALLY DESIGNING SELECTIVE MOLECULES
    6.
    发明申请
    AUTOMATICALLY DESIGNING SELECTIVE MOLECULES 有权

    公开(公告)号：US20220270705A1

    公开(公告)日：2022-08-25

    申请号：US17185148

    申请日：2021-02-25

    Applicant: International Business Machines Corporation

    Inventor： Enara C. Vijil ,  Payel Das ,  Inkit Padhi

    IPC: G16B15/30 ,  G06N20/00 ,  G06N3/02

    Abstract: Generating a drug molecule design by training an attribute predictor model using an embedding of a first molecular data base, training a first machine learning model using the attribute predictor, yielding a second embedding of the first molecular data base, training a binding affinity model using a second molecular database and the second embedding of the first molecular database, and generating a molecule design according to the second embedding and the binding affinity model.

    Out-of-domain sentence detection
    7.
    发明授权
    Out-of-domain sentence detection 有权

    公开(公告)号：US11023683B2

    公开(公告)日：2021-06-01

    申请号：US16293893

    申请日：2019-03-06

    Applicant: International Business Machines Corporation

    Inventor： Inkit Padhi ,  Ruijian Wang ,  Haoyu Wang ,  Saloni Potdar

    IPC: G06N3/00 ,  G06N3/08 ,  G06F40/30 ,  G06N3/04

    Abstract: A computer-implemented method includes obtaining a training data set including text data indicating one or more phrases or sentences. The computer-implemented method includes training a classifier using supervised machine learning based on the training data set and additional text data indicating one or more out-of-domain phrases or sentences. The computer-implemented method includes training an autoencoder using unsupervised machine learning based on the training data. The computer-implemented method further includes combining the classifier and the autoencoder to generate the out-of-domain sentence detector configured to generate an output indicating a classification of whether input text data corresponds to an out-of-domain sentence. The output is based on a combination of a first output of the classifier and a second output of the autoencoder.

    OUT-OF-DOMAIN SENTENCE DETECTION
    8.
    发明申请
    OUT-OF-DOMAIN SENTENCE DETECTION 审中-公开

    公开(公告)号：US20200285702A1

    公开(公告)日：2020-09-10

    申请号：US16293893

    申请日：2019-03-06

    Applicant: International Business Machines Corporation

    Inventor： Inkit Padhi ,  Ruijian Wang ,  Haoyu Wang ,  Saloni Potdar

    IPC: G06F17/27 ,  G06N3/08 ,  G06N3/04

    Abstract: A computer-implemented method includes obtaining a training data set including text data indicating one or more phrases or sentences. The computer-implemented method includes training a classifier using supervised machine learning based on the training data set and additional text data indicating one or more out-of-domain phrases or sentences. The computer-implemented method includes training an autoencoder using unsupervised machine learning based on the training data. The computer-implemented method further includes combining the classifier and the autoencoder to generate the out-of-domain sentence detector configured to generate an output indicating a classification of whether input text data corresponds to an out-of-domain sentence. The output is based on a combination of a first output of the classifier and a second output of the autoencoder.

Patent Agency Ranking