中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.013 seconds)

    Using a neural network
    1.
    发明授权
    Using a neural network 有权

    公开(公告)号：US11468323B2

    公开(公告)日：2022-10-11

    申请号：US16756182

    申请日：2018-10-16

    Applicant: KONINKLIJKE PHILIPS N.V.

    Inventor： Vlado Menkovski ,  Asif Rahman ,  Caroline Denise Francoise Raynaud ,  Bryan Conroy ,  Dimitrios Mavroeidis ,  Erik Bresch ,  Teun van den Heuvel

    IPC: G06K9/62 ,  G06N3/08 ,  G06N20/00

    Abstract: A method, system and computer-program product for identifying neural network inputs for a neural network that may have been incorrectly processed by the neural network. A set of activation values (of a subset of neurons of a single layer) associated with a neural network input is obtained. A neural network output associated with the neural network input is also obtained. A determination is made as to whether a first and second neural network input share similar sets of activation values, but dissimilar neural network outputs or vice versa. In this way a prediction can be made as to whether one of the first and second neural network inputs has been incorrectly processed by the neural network.

    Training a neural network model
    2.
    发明授权
    Training a neural network model 有权

    公开(公告)号：US11521064B2

    公开(公告)日：2022-12-06

    申请号：US16768783

    申请日：2018-11-30

    Applicant: KONINKLIJKE PHILIPS N.V.

    Inventor： Dimitrios Mavroeidis ,  Binyam Gebrekidan Gebre ,  Stojan Trajanovski

    IPC: G06N3/08 ,  G06T7/70 ,  G06T7/00

    Abstract: A concept for training a neural network model. The concept comprises receiving training data and test data, each comprising a set of annotated images. A neural network model is trained using the training data with an initial regularization parameter. Loss functions of the neural network for both the training data and the test data are used to modify the regularization parameter, and the neural network model is retrained using the modified regularization parameter. This process is iteratively repeated until the loss functions both converge. A system, method and a computer program product embodying this concept are disclosed.

    TRAINING A NEURAL NETWORK MODEL
    3.
    发明申请
    TRAINING A NEURAL NETWORK MODEL 审中-公开

    公开(公告)号：US20200372344A1

    公开(公告)日：2020-11-26

    申请号：US16768783

    申请日：2018-11-30

    Applicant: KONINKLIJKE PHILIPS N.V.

    Inventor： Dimitrios Mavroeidis ,  Binyam Gebrekidan Gebre ,  Stojan Trajanovski

    IPC: G06N3/08 ,  G06T7/00 ,  G06T7/70

    Abstract: A concept for training a neural network model. The concept comprises receiving training data and test data, each comprising a set of annotated images. A neural network model is trained using the training data with an initial regularization parameter. Loss functions of the neural network for both the training data and the test data are used to modify the regularization parameter, and the neural network model is retrained using the modified regularization parameter. This process is iteratively repeated until the loss functions both converge. A system, method and a computer program product embodying this concept are disclosed.

    Training first and second neural network models
    7.
    发明授权
    Training first and second neural network models 有权

    公开(公告)号：US11657265B2

    公开(公告)日：2023-05-23

    申请号：US16191542

    申请日：2018-11-15

    Applicant: KONINKLIJKE PHILIPS N.V.

    Inventor： Binyam Gebre ,  Erik Bresch ,  Dimitrios Mavroeidis ,  Teun van den Heuvel ,  Ulf Grossekathöfer

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/0481

    Abstract: Described herein are systems and methods for training first and second neural network models. A system comprises a memory comprising instruction data representing a set of instructions and a processor configured to communicate with the memory and to execute the set of instructions. The set of instructions, when executed by the processor, cause the processor to set a weight in the second model based on a corresponding weight in the first model, train the second model on a first dataset, wherein the training comprises updating the weight in the second model and adjust the corresponding weight in the first model based on the updated weight in the second model.

    TRAINING FIRST AND SECOND NEURAL NETWORK MODELS
    8.
    发明申请
    TRAINING FIRST AND SECOND NEURAL NETWORK MODELS 审中-公开

    公开(公告)号：US20190156205A1

    公开(公告)日：2019-05-23

    申请号：US16191542

    申请日：2018-11-15

    Applicant: KONINKLIJKE PHILIPS N.V.

    Inventor： Binyam Gebre ,  Erik Bresch ,  Dimitrios Mavroeidis ,  Teun van den Heuvel ,  Ulf Grossekathöfer

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Described herein are systems and methods for training first and second neural network models. A system comprises a memory comprising instruction data representing a set of instructions and a processor configured to communicate with the memory and to execute the set of instructions. The set of instructions, when executed by the processor, cause the processor to set a weight in the second model based on a corresponding weight in the first model, train the second model on a first dataset, wherein the training comprises updating the weight in the second model and adjust the corresponding weight in the first model based on the updated weight in the second model.

    Determining a sleep state of a user
    9.
    发明授权
    Determining a sleep state of a user 有权

    公开(公告)号：US12201443B2

    公开(公告)日：2025-01-21

    申请号：US17549293

    申请日：2021-12-13

    Applicant: KONINKLIJKE PHILIPS N.V.

    Inventor： Dimitrios Mavroeidis ,  Ulf Grossekathoefer ,  Aki Sakari Härmä

    IPC: A61B5/00 ,  A61B5/38

    Abstract: According to an embodiment of an aspect, there is provided a computer-implemented method for determining a sleep state of a user. The method comprising receiving (S11) a physiological signal from a physiological signal detector used by the user. The method further comprising determining (S12), based on the received physiological signal, the sleep state of the user. The method further comprising calculating (S13) a reliability value associated with the determination. The reliability value being calculated based on a comparison of the received physiological signal with historic physiological signals of the same sleep state as the determined sleep state. There is further provided a device (20) and computer-readable medium (30). In accordance with the present disclosure, the sleep state of a user may be determined with greater accuracy when compared with past methods.

Patent Agency Ranking