中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.025 seconds)

    SYSTEM AND METHOD FOR ADDRESSING OVERFITTING IN A NEURAL NETWORK
    11.
    发明申请
    SYSTEM AND METHOD FOR ADDRESSING OVERFITTING IN A NEURAL NETWORK 审中-公开
    用于解决神经网络覆盖的系统和方法

    公开(公告)号：US20160335540A1

    公开(公告)日：2016-11-17

    申请号：US15222870

    申请日：2016-07-28

    Applicant: Google Inc.

    Inventor： Geoffrey E. Hinton ,  Alexander Krizhevsky ,  Ilya Sutskever ,  Nitish Srivastva

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/084 ,  G06K9/4628 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/082

    Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.

    Abstract translation: 用于训练神经网络的系统。 开关被连接到神经网络的至少一些层中的特征检测器。 对于每个训练情况，交换机根据预配置的概率随机选择性地禁用每个特征检测器。 然后对每个训练情况的权重进行归一化，以将神经网络应用于测试数据。

    NEURAL RANDOM ACCESS MACHINE
    13.
    发明申请
    NEURAL RANDOM ACCESS MACHINE 审中-公开

    公开(公告)号：US20170140264A1

    公开(公告)日：2017-05-18

    申请号：US15349898

    申请日：2016-11-11

    Applicant: Google Inc.

    Inventor： Ilya Sutskever ,  Marcin Andrychowicz ,  Karol Piotr Kurach

    IPC: G06N3/04 ,  G06F17/18 ,  G06N3/08

    CPC classification number: G06N3/0445 ,  G06F17/18 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output from a system input. In one aspect, a neural network system includes a memory storing a set of register vectors and data defining modules, wherein each module is a respective function that takes as input one or more first vectors and outputs a second vector. The system also includes a controller neural network configured to receive a neural network input for each time step and process the neural network input to generate a neural network output. The system further includes a subsystem configured to determine inputs to each of the modules, process the input to the module to generate a respective module output, determine updated values for the register vectors, and generate a neural network input for the next time step from the updated values of the register vectors.

    TRAINING NEURAL NETWORKS ON PARTITIONED TRAINING DATA
    14.
    发明申请
    TRAINING NEURAL NETWORKS ON PARTITIONED TRAINING DATA 审中-公开
    在分类培训数据上训练神经网络

    公开(公告)号：US20160098632A1

    公开(公告)日：2016-04-07

    申请号：US14877071

    申请日：2015-10-07

    Applicant: Google Inc.

    Inventor： Ilya Sutskever ,  Wojciech Zaremba

    IPC: G06N3/08

    CPC classification number: G06N3/08 ,  G06N3/0445 ,  G06N3/10

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining partitioned training data for the neural network, wherein the partitioned training data comprises a plurality of training items each of which is assigned to a respective one of a plurality of partitions, wherein each partition is associated with a respective difficulty level; and training the neural network on each of the partitions in a sequence from a partition associated with an easiest difficulty level to a partition associated with a hardest difficulty level, wherein, for each of the partitions, training the neural network comprises: training the neural network on a sequence of training items that includes training items selected from the training items in the partition interspersed with training items selected from the training items in all of the partitions.

    Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的用于训练神经网络的计算机程序。 其中一种方法包括获得用于神经网络的分区训练数据，其中分区训练数据包括多个训练项目，每个训练项目分配给多个分区中的相应一个分区，其中每个分区与相应的难度等级相关联 ; 并且将每个分区上的神经网络从与最简单难度级别相关联的分区中的序列训练到与最困难级别相关联的分区，其中，对于每个分区，训练神经网络包括：训练神经网络 在训练项目的序列上，其包括从分配有从所有分区中的训练项目中选择的训练项目的分区中的训练项目中选择的训练项目。

    System and method for generating training cases for image classification
    15.
    发明授权
    System and method for generating training cases for image classification 有权
    用于生成图像分类训练样本的系统和方法

    公开(公告)号：US09251437B2

    公开(公告)日：2016-02-02

    申请号：US13970869

    申请日：2013-08-20

    Applicant: Google Inc.

    Inventor： Alexander Krizhevsky ,  Ilya Sutskever ,  Geoffrey E. Hinton

    IPC: G06K9/62

    CPC classification number: G06K9/6255

    Abstract: A system and method for generating training images. An existing training image is associated with a classification. The system includes an image processing module that performs color-space deformation on each pixel of the existing training image and then associates the classification to the color-space deformed training image. The technique may be applied to increase the size of a training set for training a neural network.

    Abstract translation: 一种用于生成训练图像的系统和方法。 现有的训练图像与分类相关联。 该系统包括图像处理模块，其在现有训练图像的每个像素上执行颜色空间变形，然后将分类与颜色空间变形的训练图像相关联。 该技术可以用于增加用于训练神经网络的训练集的大小。

    SYSTEM AND METHOD FOR GENERATING TRAINING CASES FOR IMAGE CLASSIFICATION
    16.
    发明申请
    SYSTEM AND METHOD FOR GENERATING TRAINING CASES FOR IMAGE CLASSIFICATION 有权
    用于生成图像分类培训案例的系统和方法

    公开(公告)号：US20140177947A1

    公开(公告)日：2014-06-26

    申请号：US13970869

    申请日：2013-08-20

    Applicant: Google Inc.

    Inventor： Alexander Krizhevsky ,  Ilya Sutskever ,  Geoffrey E. Hinton

    IPC: G06K9/62

    CPC classification number: G06K9/6255

    Abstract: A system and method for generating training images. An existing training image is associated with a classification. The system includes an image processing module that performs color-space deformation on each pixel of the existing training image and then associates the classification to the color-space deformed training image. The technique may be applied to increase the size of a training set for training a neural network.

    Abstract translation: 一种用于生成训练图像的系统和方法。 现有的训练图像与分类相关联。 该系统包括图像处理模块，其在现有训练图像的每个像素上执行颜色空间变形，然后将分类与颜色空间变形的训练图像相关联。 该技术可以用于增加用于训练神经网络的训练集的大小。

    AUGMENTING NEURAL NETWORKS WITH EXTERNAL MEMORY USING REINFORCEMENT LEARNING
    17.
    发明申请
    AUGMENTING NEURAL NETWORKS WITH EXTERNAL MEMORY USING REINFORCEMENT LEARNING 审中-公开

    公开(公告)号：US20170323201A1

    公开(公告)日：2017-11-09

    申请号：US15396331

    申请日：2016-12-30

    Applicant: Google Inc.

    Inventor： Ilya Sutskever ,  Ivo Danihelka ,  Alexander Benjamin Graves ,  Gregory Duncan Wayne ,  Wojciech Zaremba

    IPC: G06N3/08 ,  G06F3/06

    CPC classification number: G06N3/08 ,  G06F3/0604 ,  G06F3/0653 ,  G06F3/0673 ,  G06N3/0445 ,  G06N3/063

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory using reinforcement learning. One of the methods includes providing an output derived from the system output portion of the neural network output as a system output in the sequence of system outputs; selecting a memory access process from a predetermined set of memory access processes for accessing the external memory from the reinforcement learning portion of the neural network output; writing and reading data from locations in the external memory in accordance with the selected memory access process using the differentiable portion of the neural network output; and combining the data read from the external memory with a next system input in the sequence of system inputs to generate a next neural network input in the sequence of neural network inputs.

    PREDICTING LIKELIHOODS OF CONDITIONS BEING SATISFIED USING RECURRENT NEURAL NETWORKS
    19.
    发明申请
    PREDICTING LIKELIHOODS OF CONDITIONS BEING SATISFIED USING RECURRENT NEURAL NETWORKS 审中-公开

    公开(公告)号：US20170308787A1

    公开(公告)日：2017-10-26

    申请号：US15588535

    申请日：2017-05-05

    Applicant: Google Inc.

    Inventor： Gregory Sean Corrado ,  Ilya Sutskever ,  Jeffrey Adgate Dean

    IPC: G06N3/04 ,  G06F19/00 ,  G06N3/063 ,  G06N3/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting likelihoods of conditions being satisfied using recurrent neural networks. One of the systems is configured to process a temporal sequence comprising a respective input at each of a plurality of time steps and comprises: one or more recurrent neural network layers; one or more logistic regression nodes, wherein each of the logistic regression nodes corresponds to a respective condition from a predetermined set of conditions, and wherein each of the logistic regression nodes is configured to, for each of the plurality of time steps: receive the network internal state for the time step; and process the network internal state for the time step in accordance with current values of a set of parameters of the logistic regression node to generate a future condition score for the corresponding condition for the time step.

Patent Agency Ranking