公开(公告)号：US20140180986A1

公开(公告)日：2014-06-26

申请号：US14015768

申请日：2013-08-30

Applicant: Google Inc.

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

IPC: G06N3/08

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。

公开(公告)号：US20170228871A1

公开(公告)日：2017-08-10

申请号：US15497378

申请日：2017-04-26

Applicant: Google Inc.

Inventor： Volodymyr Mnih ,  Geoffrey E. Hinton

IPC: G06T7/11 ,  G06K9/00 ,  G06T11/60 ,  G06K9/62

CPC classification number: G06T7/11 ,  G06K9/0063 ,  G06K9/00651 ,  G06K9/6269 ,  G06K9/6277 ,  G06N3/084 ,  G06T7/143 ,  G06T11/60 ,  G06T2207/10032 ,  G06T2207/20084 ,  G06T2207/30181

Abstract: A system and method for labelling aerial images. A neural network generates predicted map data. The parameters of the neural network are trained by optimizing an objective function which compensates for noise in the map images. The function compensates both omission noise and registration noise.

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。

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。