公开(公告)号：US09646244B2

公开(公告)日：2017-05-09

申请号：US15150091

申请日：2016-05-09

Applicant: Google Inc.

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

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

CPC classification number: G06N3/0472 ,  G06F19/00 ,  G06N3/02 ,  G06N3/0427 ,  G06N3/0445 ,  G06N3/063 ,  G16H50/20

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.

公开(公告)号：US20160241493A1

公开(公告)日：2016-08-18

申请号：US14620630

申请日：2015-02-12

Applicant: Google Inc.

Inventor： Phillip Neal Sharp ,  Prabhakar Raghavan ,  Thompson Alexander Ivor Gawley ,  Balint Miklos ,  Karol Kurach ,  Tobias Kaufmann ,  Gregory Sean Corrado ,  Làszló Lukács

IPC: H04L12/58 ,  H04L29/08

CPC classification number: H04L51/02 ,  G06F17/248 ,  G06F17/2881 ,  G06F17/3071 ,  G06Q10/107 ,  G06Q50/01 ,  H04L67/22

Abstract: Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of “original” messages of electronic communications and reply content that is included in “reply” messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

Abstract translation: 与确定对电子通信的回复的回复内容相关的方法和装置。 一些实施方式通常指向分析电子通信语料库以确定电子通信的“原始”消息的一个或多个原始消息特征与包括在那些电子通信的“回复”消息中的回复内容之间的关系。 一些实施方式通常指向提供答复文本以包括在基于通信的一个或多个消息特征与回复文本之间确定的关系的对通信的回复中。

公开(公告)号：US20140233806A1

公开(公告)日：2014-08-21

申请号：US13768257

申请日：2013-02-15

Applicant: Google Inc.

Inventor： Richard Gossweiler ,  Gregory Sean Corrado

IPC: G01C11/04

CPC classification number: G01C11/04 ,  G01C3/04 ,  G01C5/00 ,  G06F1/1686 ,  G06F1/1694 ,  G06F3/017 ,  G06F3/0481 ,  G06F2203/04806 ,  G09G5/00 ,  G09G2354/00

Abstract: A method, computer readable storage device, and apparatus for determining the distance a computing device is located from a user's face. An image of an individual is obtained. A first pupil location and a second pupil location are identified based on the obtained image. A first distance between the identified first and second pupil location is determined. A second distance between the individual and the computing device is determined based on the determined first distance between the identified first and second pupil locations.

Abstract translation: 一种用于确定计算设备位于用户面部的距离的方法，计算机可读存储设备和装置。 获得个人的图像。 基于获得的图像来识别第一光瞳位置和第二瞳孔位置。 确定所识别的第一和第二光瞳位置之间的第一距离。 基于所识别的第一和第二瞳孔位置之间确定的第一距离来确定个体和计算设备之间的第二距离。

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.

公开(公告)号：US20170300814A1

公开(公告)日：2017-10-19

申请号：US15394668

申请日：2016-12-29

Applicant: Google Inc.

Inventor： Tal Shaked ,  Rohan Anil ,  Hrishikesh Balkrishna Aradhye ,  Mustafa Ispir ,  Glen Anderson ,  Wei Chai ,  Mehmet Levent Koc ,  Jeremiah Harmsen ,  Xiaobing Liu ,  Gregory Sean Corrado ,  Tushar Deepak Chandra ,  Heng-Tze Cheng

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/084

Abstract: A system includes one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the computers to implement a combined machine learning model for processing an input including multiple features to generate a predicted output for the machine learning input. The combined model includes: a deep machine learning model configured to process the features to generate a deep model output; a wide machine learning model configured to process the features to generate a wide model output; and a combining layer configured to process the deep model output generated by the deep machine learning model and the wide model output generated by the wide machine learning model to generate the predicted output, in which the deep model and the wide model have been trained jointly on training data to generate the deep model output and the wide model output.

公开(公告)号：US20170032242A1

公开(公告)日：2017-02-02

申请号：US15150091

申请日：2016-05-09

Applicant: Google Inc.

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

IPC: G06N3/04 ,  G06N3/063

CPC classification number: G06N3/0472 ,  G06F19/00 ,  G06N3/02 ,  G06N3/0427 ,  G06N3/0445 ,  G06N3/063 ,  G16H50/20

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.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于预测利用循环神经网络满足条件的可能性。 系统中的一个被配置为在多个时间步长中的每一个处理包括相应输入的时间序列，并且包括：一个或多个循环神经网络层; 一个或多个逻辑回归节点，其中每个逻辑回归节点对应于来自预定条件集合的相应条件，并且其中每个逻辑回归节点被配置为针对多个时间步骤中的每一个：接收网络 内部状态为时间步; 并根据逻辑回归节点的一组参数的当前值处理时间步长的网络内部状态，以生成时间步长相应条件的未来条件分数。

公开(公告)号：US20170032241A1

公开(公告)日：2017-02-02

申请号：US14810368

申请日：2015-07-27

Applicant: Google Inc.

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

IPC: G06N3/04 ,  G06N3/10

CPC classification number: G06N3/04 ,  G06N3/0445 ,  G06N3/08 ,  G06N3/10 ,  G16H50/20 ,  G16H50/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using recurrent neural networks to analyze health events. One of the methods includes obtaining a first temporal sequence of health events, wherein the first temporal sequence comprises respective health-related data associated with a particular patient at each of a plurality of time steps; processing the first temporal sequence of health events using a recurrent neural network to generate a neural network output for the first temporal sequence; and generating, from the neural network output for the first temporal sequence, health analysis data that characterizes future health events that may occur after a last time step in the temporal sequence.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用循环神经网络来分析健康事件。 所述方法之一包括获得健康事件的第一时间序列，其中所述第一时间序列在多个时间步骤中的每一个步骤包括与特定患者相关联的各个健康相关数据; 使用循环神经网络处理健康事件的第一时间序列以生成用于第一时间序列的神经网络输出; 以及从用于第一时间序列的神经网络输出生成表征可能在时间序列中的最后时间步长之后发生的未来健康事件的健康分析数据。

公开(公告)号：US09336482B1

公开(公告)日：2016-05-10

申请号：US14810381

申请日：2015-07-27

Applicant: Google Inc.

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

IPC: G06N3/02 ,  G06N3/04

CPC classification number: G06N3/0472 ,  G06F19/00 ,  G06N3/02 ,  G06N3/0427 ,  G06N3/0445 ,  G06N3/063 ,  G16H50/20

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.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于预测利用循环神经网络满足条件的可能性。 系统中的一个被配置为在多个时间步长中的每一个处理包括相应输入的时间序列，并且包括：一个或多个循环神经网络层; 一个或多个逻辑回归节点，其中每个逻辑回归节点对应于来自预定条件集合的相应条件，并且其中每个逻辑回归节点被配置为针对多个时间步骤中的每一个：接收网络 内部状态为时间步; 并根据逻辑回归节点的一组参数的当前值处理时间步长的网络内部状态，以生成时间步长相应条件的未来条件分数。

公开(公告)号：US20150178383A1

公开(公告)日：2015-06-25

申请号：US14576907

申请日：2014-12-19

Applicant: Google Inc.

Inventor： Gregory Sean Corrado ,  Tomas Mikolov ,  Samy Bengio ,  Yoram Singer ,  Jonathon Shlens ,  Andrea L. Frome ,  Jeffrey Adgate Dean ,  Mohammad Norouzi

IPC: G06F17/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes obtaining data that associates each term in a vocabulary of terms with a respective high-dimensional representation of the term; obtaining classification data for a data object, wherein the classification data includes a respective score for each of a plurality of categories, and wherein each of the categories is associated with a respective category label; computing an aggregate high-dimensional representation for the data object from high-dimensional representations for the category labels associated with the categories and the respective scores; identifying a first term in the vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation; and selecting the first term as a category label for the data object.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于对数据对象进行分类。 其中一种方法包括获得将术语词汇中的每个术语与该术语的相应高维表示相关联的数据; 获取数据对象的分类数据，其中分类数据包括多个类别中的每一个的相应分数，并且其中每个类别与相应的分类标签相关联; 从与类别和相应分数相关联的类别标签的高维表示中计算数据对象的聚合高维表示; 识别具有最接近聚合高维表示的高维表示的术语词汇表中的第一项; 并选择第一项作为数据对象的类别标签。

公开(公告)号：US20200293873A1

公开(公告)日：2020-09-17

申请号：US15262959

申请日：2016-09-12

Applicant: Google Inc.

Inventor： Andrew M. Dai ,  Quoc V. Le ,  Gregory Sean Corrado

IPC: G06N3/08 ,  G06F17/27

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating document vector representations. One of the methods includes obtaining a new document; selecting a plurality of new document word sets; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system comprises: a document embedding layer and a classifier, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of new document word sets to the trained neural network system to determine the vector representation for the new document using gradient descent.