EXPLANATION OF MACHINE-LEARNED MODELS USING IMAGE TRANSLATION

    公开(公告)号:US20250157201A1

    公开(公告)日:2025-05-15

    申请号:US19020516

    申请日:2025-01-14

    Applicant: Google LLC

    Abstract: Systems and methods for identifying visual features that influence a predictive model are provided. The technology employs an image translation function to introduce a visual feature into an image to create a modified image that can be fed to a predictive model. When the predictive model generates a different prediction for a given image than it does for a modified version of that image, the image translation function can then be used to make further modified versions that exaggerate the introduced visual feature. The technology thus aids in identifying visual features that influence the predictive model so that the model's conclusions can be understood, and so that those visual features can be further studied and tested.

    Training Machine-Learned Models with Label Differential Privacy

    公开(公告)号:US20240265294A1

    公开(公告)日:2024-08-08

    申请号:US18156915

    申请日:2023-01-19

    Applicant: Google LLC

    CPC classification number: G06N20/00

    Abstract: An example method is provided for conducting differentially private communication of training data for training a machine-learned model. Initial label data can be obtained that corresponds to feature data. A plurality of label bins can be determined to respectively provide representative values for initial label values assigned to the plurality of label bins. Noised label data can be generated, based on a probability distribution over the plurality of label bins, to correspond to the initial label data, the probability distribution characterized by, for a respective noised label corresponding to a respective initial label of the initial label data, a first probability for returning a representative value of a label bin to which the respective initial label is assigned, and a second probability for returning another value. The noised label data can be communicated for training the machine-learned model.

    Explanation of machine-learned models using image translation

    公开(公告)号:US12230016B2

    公开(公告)日:2025-02-18

    申请号:US17799740

    申请日:2020-03-03

    Applicant: Google LLC

    Abstract: Systems and methods for identifying visual features that influence a predictive model are provided. The technology employs an image translation function to introduce a visual feature into an image to create a modified image that can be fed to a predictive model. When the predictive model generates a different prediction for a given image than it does for a modified version of that image, the image translation function can then be used to make further modified versions that exaggerate the introduced visual feature. The technology thus aids in identifying visual features that influence the predictive model so that the model's conclusions can be understood, and so that those visual features can be further studied and tested.

Patent Agency Ranking