知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.014 seconds)

    Semantic coherence analysis of deep neural networks
    2.
    发明授权
    Semantic coherence analysis of deep neural networks 有权

    公开(公告)号：US11816565B2

    公开(公告)日：2023-11-14

    申请号：US16792835

    申请日：2020-02-17

    Applicant: Apple Inc.

    Inventor： Moussa Doumbouya ,  Xavier Suau Cuadros ,  Luca Zappella ,  Nicholas E. Apostoloff

    IPC: G06N20/10 ,  G06N3/045 ,  G06N3/08

    CPC classification number: G06N3/08 ,  G06N3/045 ,  G06N20/10

    Abstract: Methods and apparatus are disclosed for interpreting a deep neural network (DNN) using a Semantic Coherence Analysis (SCA)-based interpretation technique. In embodiments, a multi-layered DNN that was trained for one task is analyzed using the SCA technique to select one layer in the DNN that produces salient features for another task. In embodiments, the DNN layers are tested with test samples labeled with a set of concept labels. The output features of a DNN layer are gathered and analyzed according to the concepts. In embodiments, the output is scored with a semantic coherence score, which indicates how well the layer separates the concepts, and one layer is selected from the DNN based on its semantic coherence score. In some embodiments, a support vector machine (SVM) or additional neural network may be added to the selected layer and trained to generate classification results based on the outputs of the selected layer.

    Face image generation with pose and expression control
    3.
    发明授权
    Face image generation with pose and expression control 有权

    公开(公告)号：US11475608B2

    公开(公告)日：2022-10-18

    申请号：US16983561

    申请日：2020-08-03

    Applicant: Apple Inc.

    Inventor： Barry-John Theobald ,  Nataniel Ruiz Gutierrez ,  Nicholas E. Apostoloff

    IPC: G06T11/00 ,  G06N20/00 ,  G06V40/16

    Abstract: One aspect of the disclosure is a non-transitory computer-readable storage medium including program instructions. Operations performed by execution of the program instructions include obtaining an input image that depicts a face of a subject, having an initial facial expression and an initial pose, determining a reference shape description based on the input image, determining a target shape description based on the reference shape description, a facial expression difference, and a pose difference, generating a rendered target shape image using the target shape description, and generating an output image based on the input image and the rendered target shape using an image generator, wherein the output image is a simulated image of the subject of the input image that has a final expression that is based on the initial facial expression and the facial expression difference, and a final pose that is based on the initial pose and the pose difference.

    Face Image Generation With Pose And Expression Control
    5.
    发明申请
    Face Image Generation With Pose And Expression Control 有权

    公开(公告)号：US20210097730A1

    公开(公告)日：2021-04-01

    申请号：US16983561

    申请日：2020-08-03

    Applicant: Apple Inc.

    Inventor： Barry-John Theobald ,  Nataniel Ruiz Gutierrez ,  Nicholas E. Apostoloff

    IPC: G06T11/00 ,  G06K9/00 ,  G06N20/00

    Abstract: One aspect of the disclosure is a non-transitory computer-readable storage medium including program instructions. Operations performed by execution of the program instructions include obtaining an input image that depicts a face of a subject, having an initial facial expression and an initial pose, determining a reference shape description based on the input image, determining a target shape description based on the reference shape description, a facial expression difference, and a pose difference, generating a rendered target shape image using the target shape description, and generating an output image based on the input image and the rendered target shape using an image generator, wherein the output image is a simulated image of the subject of the input image that has a final expression that is based on the initial facial expression and the facial expression difference, and a final pose that is based on the initial pose and the pose difference.

    Interpretable neural networks for cuffless blood pressure estimation
    6.
    发明授权
    Interpretable neural networks for cuffless blood pressure estimation 有权

    公开(公告)号：US12165052B2

    公开(公告)日：2024-12-10

    申请号：US16945695

    申请日：2020-07-31

    Applicant: Apple Inc.

    Inventor： Siddharth Khullar ,  Nicholas E. Apostoloff ,  Amruta Pai

    IPC: G06N3/08 ,  G06N3/045 ,  G16H40/60

    Abstract: In some examples, an individually-pruned neural network can estimate blood pressure from a seismocardiogram (SCG). In some examples, a baseline model can be constructed by training the model with SCG data and blood pressure measurement from a plurality of subjects. One or more filters (e.g., the filters in the top layer of the network) can be ranked by separability, which can be used to prune the model for each unseen user that uses the model thereafter, for example. In some examples, individuals can use individually-pruned models to calculate blood pressure using SCG data without corresponding blood pressure measurements.

    SEMANTIC COHERENCE ANALYSIS OF DEEP NEURAL NETWORKS
    8.
    发明申请
    SEMANTIC COHERENCE ANALYSIS OF DEEP NEURAL NETWORKS 有权

    公开(公告)号：US20210117778A1

    公开(公告)日：2021-04-22

    申请号：US16792835

    申请日：2020-02-17

    Applicant: Apple Inc.

    Inventor： Moussa Doumbouya ,  Xavier Suau Cuadros ,  Luca Zappella ,  Nicholas E. Apostoloff

    IPC: G06N3/08 ,  G06N3/04 ,  G06N20/10

    Abstract: Methods and apparatus are disclosed for interpreting a deep neural network (DNN) using a Semantic Coherence Analysis (SCA)-based interpretation technique. In embodiments, a multi-layered DNN that was trained for one task is analyzed using the SCA technique to select one layer in the DNN that produces salient features for another task. In embodiments, the DNN layers are tested with test samples labeled with a set of concept labels. The output features of a DNN layer are gathered and analyzed according to the concepts. In embodiments, the output is scored with a semantic coherence score, which indicates how well the layer separates the concepts, and one layer is selected from the DNN based on its semantic coherence score. In some embodiments, a support vector machine (SVM) or additional neural network may be added to the selected layer and trained to generate classification results based on the outputs of the selected layer.

Patent Agency Ranking