中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

18 records (took 0.013 seconds)

    Highly Efficient Convolutional Neural Networks
    3.
    发明申请
    Highly Efficient Convolutional Neural Networks 审中-公开

    公开(公告)号：US20190147318A1

    公开(公告)日：2019-05-16

    申请号：US15898566

    申请日：2018-02-17

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/08

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    Parameter-efficient multi-task and transfer learning
    6.
    发明授权
    Parameter-efficient multi-task and transfer learning 有权

    公开(公告)号：US11676008B2

    公开(公告)日：2023-06-13

    申请号：US16577698

    申请日：2019-09-20

    Applicant: Google LLC

    Inventor： Mark Sandler ,  Andrey Zhmoginov ,  Andrew Gerald Howard ,  Pramod Kaushik Mudrakarta

    IPC: G10L15/16 ,  G06N3/08 ,  G06N3/045

    CPC classification number: G06N3/08 ,  G06N3/045 ,  G10L15/16

    Abstract: The present disclosure provides systems and methods that enable parameter-efficient transfer learning, multi-task learning, and/or other forms of model re-purposing such as model personalization or domain adaptation. In particular, as one example, a computing system can obtain a machine-learned model that has been previously trained on a first training dataset to perform a first task. The machine-learned model can include a first set of learnable parameters. The computing system can modify the machine-learned model to include a model patch, where the model patch includes a second set of learnable parameters. The computing system can train the machine-learned model on a second training dataset to perform a second task that is different from the first task, which may include learning new values for the second set of learnable parameters included in the model patch while keeping at least some (e.g., all) of the first set of parameters fixed.

    Highly efficient convolutional neural networks
    7.
    发明授权
    Highly efficient convolutional neural networks 有权

    公开(公告)号：US11823024B2

    公开(公告)日：2023-11-21

    申请号：US17382503

    申请日：2021-07-22

    Applicant: Google LLC

    Inventor： Andrew Gerald Howard ,  Mark Sandler ,  Liang-Chieh Chen ,  Andrey Zhmoginov ,  Menglong Zhu

    IPC: G06N3/04 ,  G06N3/08 ,  G06N3/045 ,  G06N3/048

    CPC classification number: G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N3/048

    Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

    Parameter-Efficient Multi-Task and Transfer Learning
    8.
    发明公开
    Parameter-Efficient Multi-Task and Transfer Learning 审中-公开

    公开(公告)号：US20230267330A1

    公开(公告)日：2023-08-24

    申请号：US18310638

    申请日：2023-05-02

    Applicant: Google LLC

    Inventor： Mark Sandler ,  Andrew Gerald Howard ,  Andrey Zhmoginov ,  Pramod Kaushik Mudrakarta

    IPC: G06N3/08 ,  G06N3/045

    CPC classification number: G06N3/08 ,  G06N3/045 ,  G10L15/16

    Abstract: The present disclosure provides systems and methods that enable parameter-efficient transfer learning, multi-task learning, and/or other forms of model re-purposing such as model personalization or domain adaptation. In particular, as one example, a computing system can obtain a machine-learned model that has been previously trained on a first training dataset to perform a first task. The machine-learned model can include a first set of learnable parameters. The computing system can modify the machine-learned model to include a model patch, where the model patch includes a second set of learnable parameters. The computing system can train the machine-learned model on a second training dataset to perform a second task that is different from the first task, which may include learning new values for the second set of learnable parameters included in the model patch while keeping at least some (e.g., all) of the first set of parameters fixed.

    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS
    9.
    发明公开
    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS 审中-公开

    公开(公告)号：US20230237314A1

    公开(公告)日：2023-07-27

    申请号：US18114333

    申请日：2023-02-27

    Applicant: Google LLC

    Inventor： Francois Chollet ,  Andrew Gerald Howard

    IPC: G06N3/0464 ,  G06V10/82

    CPC classification number: G06N3/0464 ,  G06V10/82

    Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS
    10.
    发明申请
    IMAGE PROCESSING NEURAL NETWORKS WITH SEPARABLE CONVOLUTIONAL LAYERS 有权

    公开(公告)号：US20210027140A1

    公开(公告)日：2021-01-28

    申请号：US16338963

    申请日：2017-10-06

    Applicant: Google LLC

    Inventor： Francois Chollet ,  Andrew Gerald Howard

    IPC: G06N3/04 ,  G06N3/08

    Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

Patent Agency Ranking