中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.019 seconds)

    INPUT SPACE CERTIFICATION FOR A BLACK BOX MACHINE LEARNING MODEL
    1.
    发明申请
    INPUT SPACE CERTIFICATION FOR A BLACK BOX MACHINE LEARNING MODEL 有权

    公开(公告)号：US20250156299A1

    公开(公告)日：2025-05-15

    申请号：US18509625

    申请日：2023-11-15

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Amit Dhurandhar ,  Swagatam Haldar ,  Dennis Wei ,  Karthikeyan Natesan Ramamurthy

    IPC: G06F11/34

    Abstract: A method, computer program product, and computer system for certifying a d-dimensional input space x for a black box machine learning model. Triggered is execution of a first process that certifies, with respect to the model, a maximum subspace of x that is characterized by a largest half-width or radius (w) centered at x=x0. Received from of the first process are: w and both (i) a point re selected from multiple points r randomly sampled in the maximum subspace, and (ii) a quality metric f(re), where re and f(re) were previously determined from the model having been queried for each point r randomly sampled in the maximum subspace, where re is selected on a basis of f(re) satisfying f(re)≥θ for a specified quality threshold θ. The model is executed for input confined to the maximum subspace, which performs a practical application procedure that improves performance of the model.

    OPTIMIZED SCORE TRANSFORMATION FOR FAIR CLASSIFICATION
    4.
    发明申请
    OPTIMIZED SCORE TRANSFORMATION FOR FAIR CLASSIFICATION 有权

    公开(公告)号：US20210374581A1

    公开(公告)日：2021-12-02

    申请号：US16888413

    申请日：2020-05-29

    Applicant: International Business Machines Corporation ,  President and Fellows of Harvard College

    Inventor： Dennis Wei ,  Karthikeyan Natesan Ramamurthy ,  Flavio du Pin Calmon

    IPC: G06N7/00 ,  G06N20/00

    Abstract: Obtain, from an existing machine learning classifier, original probabilistic scores classifying samples taken from two or more groups into two or more classes via supervised machine learning. Associate the original probabilistic scores with a plurality of original Lagrange multipliers. Adjust values of the plurality of original Lagrange multipliers via low-dimensional convex optimization to obtain updated Lagrange multipliers that satisfy fairness constraints as compared to the original Lagrange multipliers. Based on the updated Lagrange multipliers, closed-form transform the original probabilistic scores into transformed probabilistic scores that satisfy the fairness constraints while minimizing loss in utility. The fairness constraints are with respect to the two or more groups.

    MOVING DECISION BOUNDARIES IN MACHINE LEARNING MODELS
    8.
    发明申请
    MOVING DECISION BOUNDARIES IN MACHINE LEARNING MODELS 有权

    公开(公告)号：US20220358397A1

    公开(公告)日：2022-11-10

    申请号：US17308310

    申请日：2021-05-05

    Applicant: International Business Machines Corporation

    Inventor： Oznur Alkan ,  Elizabeth Daly ,  Rahul Nair ,  Massimiliano Mattetti ,  Dennis Wei ,  Karthikeyan Natesan Ramamurthy

    IPC: G06N20/00 ,  G06N5/04

    Abstract: Embodiments are disclosed for a method. The method includes receiving feedback decision rules for multiple predictions by a trained machine learning model. generating a feedback rule set based on the feedback decision rules. The method further includes generating an updated training dataset based on an original training dataset and an updated feedback rule set. The updated feedback rule set resolves one or more conflicts of the feedback rule set, and the updated training dataset is configured to train the machine learning model to move a decision boundary. Generating the updated training dataset includes generating multiple updated training instances by applying one of the feedback decision rules to a training instance of the original training dataset.

Patent Agency Ranking