中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

53 records (took 0.028 seconds)

    META-LEARNING FOR MULTI-TASK LEARNING FOR NEURAL NETWORKS
    32.
    发明申请
    META-LEARNING FOR MULTI-TASK LEARNING FOR NEURAL NETWORKS 有权

    公开(公告)号：US20210406609A1

    公开(公告)日：2021-12-30

    申请号：US17344758

    申请日：2021-06-10

    Applicant: Magic Leap, Inc.

    Inventor： Andrew Rabinovich ,  Vijay Badrinarayanan ,  Srivignesh Rajendran ,  Chen-Yu Lee

    IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods and systems for meta-learning are described for automating learning of child tasks with a single neural network. The order in which tasks are learned by the neural network can affect performance of the network, and the meta-learning approach can use a task-level curriculum for multi-task training. The task-level curriculum can be learned by monitoring a trajectory of loss functions during training. The meta-learning approach can learn to adapt task loss balancing weights in the course of training to get improved performance on multiple tasks on real world datasets. Advantageously, learning to dynamically balance weights among different task losses can lead to superior performance over the use of static weights determined by expensive random searches or heuristics. Embodiments of the meta-learning approach can be used for computer vision tasks or natural language processing tasks, and the trained neural networks can be used by augmented or virtual reality devices.

    Meta-learning for multi-task learning for neural networks
    33.
    发明授权
    Meta-learning for multi-task learning for neural networks 有权

    公开(公告)号：US11048978B2

    公开(公告)日：2021-06-29

    申请号：US16185582

    申请日：2018-11-09

    Applicant: Magic Leap, Inc.

    Inventor： Andrew Rabinovich ,  Vijay Badrinarayanan ,  Srivignesh Rajendran ,  Chen-Yu Lee

    IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods and systems for meta-learning are described for automating learning of child tasks with a single neural network. The order in which tasks are learned by the neural network can affect performance of the network, and the meta-learning approach can use a task-level curriculum for multi-task training. The task-level curriculum can be learned by monitoring a trajectory of loss functions during training. The meta-learning approach can learn to adapt task loss balancing weights in the course of training to get improved performance on multiple tasks on real world datasets. Advantageously, learning to dynamically balance weights among different task losses can lead to superior performance over the use of static weights determined by expensive random searches or heuristics. Embodiments of the meta-learning approach can be used for computer vision tasks or natural language processing tasks, and the trained neural networks can be used by augmented or virtual reality devices.

    GRADIENT ADVERSARIAL TRAINING OF NEURAL NETWORKS
    34.
    发明申请
    GRADIENT ADVERSARIAL TRAINING OF NEURAL NETWORKS 有权

    公开(公告)号：US20210192357A1

    公开(公告)日：2021-06-24

    申请号：US17051982

    申请日：2019-05-15

    Applicant: Magic Leap, Inc.

    Inventor： Ayan Tuhinendu Sinha ,  Andrew Rabinovich ,  Zhao Chen ,  Vijay Badrinarayanan

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Systems and methods for gradient adversarial training of a neural network are disclosed. In one aspect of gradient adversarial training, an auxiliary neural network can be trained to classify a gradient tensor that is evaluated during backpropagation in a main neural network that provides a desired task output. The main neural network can serve as an adversary to the auxiliary network in addition to a standard task-based training procedure. The auxiliary neural network can pass an adversarial gradient signal back to the main neural network, which can use this signal to regularize the weight tensors in the main neural network. Gradient adversarial training of the neural network can provide improved gradient tensors in the main network. Gradient adversarial techniques can be used to train multitask networks, knowledge distillation networks, and adversarial defense networks.

    PERIOCULAR TEST FOR MIXED REALITY CALIBRATION
    36.
    发明申请
    PERIOCULAR TEST FOR MIXED REALITY CALIBRATION 审中-公开

    公开(公告)号：US20200250872A1

    公开(公告)日：2020-08-06

    申请号：US16780698

    申请日：2020-02-03

    Applicant: Magic Leap, Inc.

    Inventor： Adrian Kaehler ,  Gary Bradski ,  Vijay Badrinarayanan

    IPC: G06T11/60 ,  G06K9/46 ,  G06K9/00 ,  G06T3/20 ,  G02B27/01

    Abstract: A wearable device can include an inward-facing imaging system configured to acquire images of a user's periocular region. The wearable device can determine a relative position between the wearable device and the user's face based on the images acquired by the inward-facing imaging system. The relative position may be used to determine whether the user is wearing the wearable device, whether the wearable device fits the user, or whether an adjustment to a rendering location of virtual object should be made to compensate for a deviation of the wearable device from its normal resting position.

    NEURAL NETWORK FOR EYE IMAGE SEGMENTATION AND IMAGE QUALITY ESTIMATION
    37.
    发明申请
    NEURAL NETWORK FOR EYE IMAGE SEGMENTATION AND IMAGE QUALITY ESTIMATION 审中-公开

    公开(公告)号：US20200005462A1

    公开(公告)日：2020-01-02

    申请号：US16570418

    申请日：2019-09-13

    Applicant: Magic Leap, Inc.

    Inventor： Alexey Spizhevoy ,  Adrian Kaehler ,  Vijay Badrinarayanan

    IPC: G06T7/10 ,  G06K9/00 ,  G06T7/00

    Abstract: Systems and methods for eye image segmentation and image quality estimation are disclosed. In one aspect, after receiving an eye image, a device such as an augmented reality device can process the eye image using a convolutional neural network with a merged architecture to generate both a segmented eye image and a quality estimation of the eye image. The segmented eye image can include a background region, a sclera region, an iris region, or a pupil region. In another aspect, a convolutional neural network with a merged architecture can be trained for eye image segmentation and image quality estimation. In yet another aspect, the device can use the segmented eye image to determine eye contours such as a pupil contour and an iris contour. The device can use the eye contours to create a polar image of the iris region for computing an iris code or biometric authentication.

    GRADIENT NORMALIZATION SYSTEMS AND METHODS FOR ADAPTIVE LOSS BALANCING IN DEEP MULTITASK NETWORKS
    38.
    发明申请
    GRADIENT NORMALIZATION SYSTEMS AND METHODS FOR ADAPTIVE LOSS BALANCING IN DEEP MULTITASK NETWORKS 审中-公开

    公开(公告)号：US20190130275A1

    公开(公告)日：2019-05-02

    申请号：US16169840

    申请日：2018-10-24

    Applicant: Magic Leap, Inc.

    Inventor： Zhao Chen ,  Vijay Badrinarayanan ,  Andrew Rabinovich

    IPC: G06N3/08 ,  G06N3/04 ,  G06F15/18

    Abstract: Systems and methods for training a multitask network is disclosed. In one aspect, training the multitask network includes determining a gradient norm of a single-task loss adjusted by a task weight for each task, with respect to network weights of the multitask network, and a relative training rate for the task based on the single-task loss for the task. Subsequently, a gradient loss function, comprising a difference between (1) the determined gradient norm for each task and (2) a corresponding target gradient norm, can be determined. An updated task weight for the task can be determined and used in the next iteration of training the multitask network, using a gradient of the gradient loss function with respect to the task weight for the task.

    TRAINING A NEURAL NETWORK WITH REPRESENTATIONS OF USER INTERFACE DEVICES
    39.
    发明申请
    TRAINING A NEURAL NETWORK WITH REPRESENTATIONS OF USER INTERFACE DEVICES 审中-公开

    公开(公告)号：US20190034765A1

    公开(公告)日：2019-01-31

    申请号：US15994599

    申请日：2018-05-31

    Applicant: Magic Leap, Inc.

    Inventor： Adrian Kaehler ,  Gary Bradski ,  Vijay Badrinarayanan

    IPC: G06K9/62 ,  G06F3/01 ,  G06T7/70 ,  G06T19/00 ,  G06K9/00 ,  G06F3/0481 ,  G06N3/08

    Abstract: Disclosed herein are examples of a wearable display system capable of determining a user interface (UI) event with respect to a virtual UI device (e.g., a button) and a pointer (e.g., a finger or a stylus) using a neural network. The wearable display system can render a representation of the UI device onto an image of the pointer captured when the virtual UI device is shown to the user and the user uses the pointer to interact with the virtual UI device. The representation of the UI device can include concentric shapes (or shapes with similar or the same centers of gravity) of high contrast. The neural network can be trained using training images with representations of virtual UI devices and pointers.

Patent Agency Ranking