中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.015 seconds)

    Prototype-based machine learning reasoning interpretation
    1.
    发明授权
    Prototype-based machine learning reasoning interpretation 有权

    公开(公告)号：US11610085B2

    公开(公告)日：2023-03-21

    申请号：US16289520

    申请日：2019-02-28

    Applicant: ADOBE INC.

    Inventor： Deepak Pai ,  Debraj Debashish Basu ,  Joshua Alan Sweetkind-Singer

    IPC: G06K9/62 ,  G06N20/00 ,  G06F11/30

    Abstract: In some examples, a prototype model that includes a representative subset of data points (e.g., inputs and output classifications) of a machine learning model is analyzed to efficiently interpret the machine learning model's behavior. Performance metrics such as a critic fraction, local explanation scores, and global explanation scores are determined. A local explanation score capture an importance of a feature of a test point to the machine learning model determining a particular class for the test point and is computed by comparing a value of a feature of a test point to values for prototypes of the prototype model. Using a similar approach, global explanation scores may be computed for features by combining local explanation scores for data points. A critic fraction may be computed to quantify a misclassification rate of the prototype model, indicating the interpretability of the model.

    QUANTIFYING AND IMPROVING THE PERFORMANCE OF COMPUTATION-BASED CLASSIFIERS
    3.
    发明申请
    QUANTIFYING AND IMPROVING THE PERFORMANCE OF COMPUTATION-BASED CLASSIFIERS 有权

    公开(公告)号：US20220300557A1

    公开(公告)日：2022-09-22

    申请号：US17203300

    申请日：2021-03-16

    Applicant: ADOBE INC.

    Inventor： Debraj Debashish Basu ,  Ganesh Satish Mallya ,  Shankar Venkitachalam ,  Deepak Pai

    IPC: G06F16/906 ,  G06F16/9035 ,  G06F16/901

    Abstract: Enhanced methods for improving the performance of classifiers are described. A ground-truth labeled dataset is accessed. A classifier predicts a predicted label for datapoints of the dataset. A confusion matrix for the dataset and classifier is generated. A credibility interval is determined for a performance metric for each label. A first labels with a sufficiently large credibility interval is identified. A second label is identified, where the classifier is likely to confuse, in its predictions, the first label with the second label. The identification of the second label is based on instances of incorrect label predictions of the classifier for the first and/or the second labels. The classifier is updated based on a new third label that includes an aggregation of the first label and the second label. The updated classifier model predicts the third label for any datapoint that the classifier previously predicted the first or second labels.

    PROTOTYPE-BASED MACHINE LEARNING REASONING INTERPRETATION
    5.
    发明申请
    PROTOTYPE-BASED MACHINE LEARNING REASONING INTERPRETATION 审中-公开

    公开(公告)号：US20200279140A1

    公开(公告)日：2020-09-03

    申请号：US16289520

    申请日：2019-02-28

    Applicant: ADOBE INC.

    Inventor： Deepak Pai ,  Debraj Debashish Basu ,  Joshua Alan Sweetkind-Singer

    IPC: G06K9/62 ,  G06N20/00 ,  G06N5/04 ,  G06F11/30

    Abstract: In some examples, a prototype model that includes a representative subset of data points (e.g., inputs and output classifications) of a machine learning model is analyzed to efficiently interpret the machine learning model's behavior. Performance metrics such as a critic fraction, local explanation scores, and global explanation scores are determined. A local explanation score capture an importance of a feature of a test point to the machine learning model determining a particular class for the test point and is computed by comparing a value of a feature of a test point to values for prototypes of the prototype model. Using a similar approach, global explanation scores may be computed for features by combining local explanation scores for data points. A critic fraction may be computed to quantify a misclassification rate of the prototype model, indicating the interpretability of the model.

    IDENTIFYING SALIENT REGIONS BASED ON MULTI-RESOLUTION PARTITIONING
    6.
    发明申请
    IDENTIFYING SALIENT REGIONS BASED ON MULTI-RESOLUTION PARTITIONING 有权

    公开(公告)号：US20250078220A1

    公开(公告)日：2025-03-06

    申请号：US18458778

    申请日：2023-08-30

    Applicant: Adobe Inc.

    Inventor： Sriram Ravindran ,  Debraj Debashish Basu

    IPC: G06T5/00 ,  G06V10/46 ,  G06V10/82

    Abstract: In implementation of techniques for generating salient regions based on multi-resolution partitioning, a computing device implements a salient object system to receive a digital image including a salient object. The salient object system generates a first mask for the salient object by partitioning the digital image into salient and non-salient regions. The salient object system also generates a second mask for the salient object that has a resolution that is different than the first mask by partitioning a resampled version of the digital image into salient and non-salient regions. Based on the first mask and the second mask, the salient object system generates an indication of a salient region of the digital image using a machine learning model. The salient object system then displays the indication of the salient region in a user interface.

    Generating weighted contextual themes to guide unsupervised keyphrase relevance models
    7.
    发明授权
    Generating weighted contextual themes to guide unsupervised keyphrase relevance models 有权

    公开(公告)号：US12190621B2

    公开(公告)日：2025-01-07

    申请号：US17653414

    申请日：2022-03-03

    Applicant: Adobe Inc.

    Inventor： Debraj Debashish Basu ,  Shankar Venkitachalam ,  Vinh Khuc ,  Deepak Pai

    IPC: G06F17/00 ,  G06F40/295 ,  G06N20/00 ,  G06V30/19 ,  G06V30/416

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize intelligent contextual bias weights for informing keyphrase relevance models to extract keyphrases. For example, the disclosed systems generate a graph from a digital document by mapping words from the digital document to nodes of the graph. In addition, the disclosed systems determine named entity bias weights for the nodes of the graph utilizing frequencies with which the words corresponding to the nodes appear within named entities identified from the digital document. Moreover, the disclosed systems generate a keyphrase summary for the digital document utilizing the graph and a machine learning model biased according to the named entity bias weights for the nodes of the graph.

Patent Agency Ranking