公开(公告)号：US10521718B1

公开(公告)日：2019-12-31

申请号：US15279268

申请日：2016-09-28

Applicant: Google Inc.

Inventor： Christian Szegedy ,  Ian Goodfellow

IPC: G06N3/08 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

公开(公告)号：US20170334066A1

公开(公告)日：2017-11-23

申请号：US15596103

申请日：2017-05-16

Applicant: Google Inc.

Inventor： Sergey Levine ,  Chelsea Finn ,  Ian Goodfellow

IPC: B25J9/16

CPC classification number: B25J9/161 ,  B25J9/1656 ,  B25J9/1697 ,  G05B13/027 ,  G05B2219/39289 ,  G06K9/00 ,  G06K9/00335 ,  G06K9/4628 ,  G06N3/008 ,  G06N3/0454 ,  G06N3/084 ,  G06T7/74 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30164

Abstract: Some implementations of this specification are directed generally to deep machine learning methods and apparatus related to predicting motion(s) (if any) that will occur to object(s) in an environment of a robot in response to particular movement of the robot in the environment. Some implementations are directed to training a deep neural network model to predict at least one transformation (if any), of an image of a robot's environment, that will occur as a result of implementing at least a portion of a particular movement of the robot in the environment. The trained deep neural network model may predict the transformation based on input that includes the image and a group of robot movement parameters that define the portion of the particular movement.

公开(公告)号：US08965112B1

公开(公告)日：2015-02-24

申请号：US14108474

申请日：2013-12-17

Applicant: Google Inc.

Inventor： Julian Ibarz ,  Yaroslav Bulatov ,  Ian Goodfellow

IPC: G06K9/62

CPC classification number: G06K9/6256 ,  G06K9/3258 ,  G06K9/6273 ,  G06K9/6277

Abstract: Systems and methods for sequence transcription with neural networks are provided. More particularly, a neural network can be implemented to map a plurality of training images received by the neural network into a probabilistic model of sequences comprising P(S|X) by maximizing log P(S|X) on the plurality of training images. X represents an input image and S represents an output sequence of characters for the input image. The trained neural network can process a received image containing characters associated with building numbers. The trained neural network can generate a predicted sequence of characters by processing the received image.

Abstract translation: 提供了使用神经网络进行序列转录的系统和方法。 更具体地，可以实现神经网络，以通过使多个训练图像上的对数P（S | X）最大化来将由神经网络接收的多个训练图像映射到包括P（S | X）的序列的概率模型中。 X表示输入图像，S表示输入图像的字符的输出序列。 经训练的神经网络可以处理包含与建筑物号码相关联的字符的接收图像。 经训练的神经网络可以通过处理接收的图像来生成预测的字符序列。

公开(公告)号：US11173599B2

公开(公告)日：2021-11-16

申请号：US15596103

申请日：2017-05-16

Applicant: Google Inc.

Inventor： Sergey Levine ,  Chelsea Finn ,  Ian Goodfellow

IPC: G06N3/08 ,  G06N3/00 ,  G06N3/04 ,  B25J9/16 ,  G05B13/02 ,  G06K9/46 ,  G06K9/00 ,  G06T7/73

Abstract: Some implementations of this specification are directed generally to deep machine learning methods and apparatus related to predicting motion(s) (if any) that will occur to object(s) in an environment of a robot in response to particular movement of the robot in the environment. Some implementations are directed to training a deep neural network model to predict at least one transformation (if any), of an image of a robot's environment, that will occur as a result of implementing at least a portion of a particular movement of the robot in the environment. The trained deep neural network model may predict the transformation based on input that includes the image and a group of robot movement parameters that define the portion of the particular movement.

公开(公告)号：US09454714B1

公开(公告)日：2016-09-27

申请号：US14587088

申请日：2014-12-31

Applicant: Google Inc.

Inventor： Julian Ibarz ,  Yaroslav Bulatov ,  Ian Goodfellow

IPC: G06K9/62

CPC classification number: G06K9/6256 ,  G06K9/3258 ,  G06K9/6273 ,  G06K9/6277

Abstract: Systems and methods for sequence transcription with neural networks are provided. More particularly, a neural network can be implemented to map a plurality of training images received by the neural network into a probabilistic model of sequences comprising P(S|X) by maximizing log P(S|X) on the plurality of training images. X represents an input image and S represents an output sequence of characters for the input image. The trained neural network can process a received image containing characters associated with building numbers. The trained neural network can generate a predicted sequence of characters by processing the received image.

公开(公告)号：US20170140272A1

公开(公告)日：2017-05-18

申请号：US15349901

申请日：2016-11-11

Applicant: Google Inc.

Inventor： Ian Goodfellow ,  Tianqi Chen ,  Jonathon Shlens

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a larger neural network from a smaller neural network. In one aspect, a method includes obtaining data specifying an original neural network; generating a larger neural network from the original neural network, wherein the larger neural network has a larger neural network structure including the plurality of original neural network units and a plurality of additional neural network units not in the original neural network structure; initializing values of the parameters of the original neural network units and the additional neural network units so that the larger neural network generates the same outputs from the same inputs as the original neural network; and training the larger neural network to determine trained values of the parameters of the original neural network units and the additional neural network units from the initialized values.