-
公开(公告)号：US20160012331A1
公开(公告)日：2016-01-14
申请号：US14860462
申请日：2015-09-21
Applicant: Google Inc.
Inventor： Kai Chen , Xiaodan Song , Gregory S. Corrado , Kun Zhang , Jeffrey A. Dean , Bahman Rabii
CPC classification number: G06N3/084 , G06F17/30707 , G06F17/30864 , G06N3/04 , G06N3/0427 , G06N3/08 , G06Q30/02
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.
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，用于使用深层网络评分概念术语。 所述方法之一包括接收包括资源的多个特征的输入，其中每个特征是所述资源的相应属性的值; 使用相应的嵌入功能处理每个特征以生成一个或多个数值; 处理所述数值以产生所述资源的特征的替代表示，其中处理所述浮点值包括将一个或多个非线性变换应用于所述浮点值; 以及处理所述输入的替代表示，以在预定概念术语集中为每个概念项产生相应的相关性得分，其中各个相关性分数中的每一个测量相应概念项与资源的预测相关性。
-
公开(公告)号：US09218573B1
公开(公告)日：2015-12-22
申请号：US13826327
申请日：2013-03-14
Applicant: Google Inc.
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Samy Bengio , Rajat Monga , Matthieu Devin
CPC classification number: G06N99/005 , G06K9/6256 , G06K9/6269 , G06N3/063 , G06N3/08 , G06N5/025 , G06N7/005 , G06N7/08
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.
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，用于使用参数服务器分片训练模型。 其中一种方法包括在被配置为维持模型的参数的不相交分区的值的参数服务器分片上接收来自模型的多个副本中的每一个的参数值的相继请求; 响应于每个请求，将每个请求的参数的当前值下载到从其接收请求的副本; 接收连续的上传，每次上传包括由分片保存的分区中的每个参数的各自的增量值; 并且根据增量值的上载重复地更新由参数服务器分片保存的分区中的参数的值，以生成当前参数值。
-
公开(公告)号：US08768870B1
公开(公告)日：2014-07-01
申请号：US13968019
申请日：2013-08-15
Applicant: Google Inc.
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Samy Bengio , Rajat Monga , Matthieu Devin
IPC: G06F15/18
CPC classification number: G06N99/005 , G06K9/6256 , G06K9/6269 , G06N3/063 , G06N3/08 , G06N5/025 , G06N7/005 , G06N7/08
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.
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，用于使用参数服务器分片训练模型。 其中一种方法包括在被配置为维持模型的参数的不相交分区的值的参数服务器分片上接收来自模型的多个副本中的每一个的参数值的相继请求; 响应于每个请求，将每个请求的参数的当前值下载到从其接收请求的副本; 接收连续的上传，每次上传包括由分片保存的分区中的每个参数的各自的增量值; 并且根据增量值的上载重复地更新由参数服务器分片保存的分区中的参数的值，以生成当前参数值。
-
公开(公告)号：US20170364822A1
公开(公告)日：2017-12-21
申请号：US15183335
申请日：2016-06-15
Applicant: Google Inc.
Inventor： Scott Tadashi Davis , Kai Chen , Michael Jee-Kai Wang , Wei Jiang , Maryam Tavafi , Peter Zaimis Tipton
CPC classification number: G06N20/00 , G06F16/22 , G06F16/435 , G06Q30/0261 , H04L67/06 , H04L67/42
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing content presentation. In one aspect, a system includes a training database that stores training data including attribute information about users and corresponding proxy metrics quantifying behavior by the users following content presentation; a content database; a model generator that accesses the training data and trains a model for content distribution; and a content distribution server that receives a content request, uses the model to select content, transmits data identifying the selected content, wherein the model: obtains a set of attributes for a user associated with the request, receives information about a given content, predicts a proxy metric based on the set of attributes and the information about the content, the predicted proxy metric providing information about subject retention or awareness; and identifies the given content for distribution if the predicted proxy metrics meet a threshold.
-
15.发明授权公开(公告)号：US09514098B1
公开(公告)日：2016-12-06
申请号：US14141182
申请日：2013-12-26
Applicant: Google Inc.
Inventor： Amarnag Subramanya , Jingyi Liu , Fernando Carlos das Neves Pereira , Kai Chen , Jay Ponte , Rami Al-Rfou′
IPC: G06F17/21
CPC classification number: G06F17/21 , G06F17/277 , G06F17/278
Abstract: Methods and apparatus related to determining coreference resolution using distributed word representations. Distributed word representations, indicative of syntactic and semantic features, may be identified for one or more noun phrases. For each of the one or more noun phrases, a referring feature representation and an antecedent feature representation may be determined, where the referring feature representation includes the distributed word representation, and the antecedent feature representation includes the distributed word representation augmented by one or more antecedent features. In some implementations the referring feature representation may be augmented by one or more referring features. Coreference embeddings of the referring and antecedent feature representations of the one or more noun phrases may be learned. Distance measures between two noun phrases may be determined based on the coreference embeddings.
Abstract translation: 与使用分布式字表示法确定协同解析相关的方法和设备。 可以为一个或多个名词短语识别表示句法和语义特征的分布式词表示。 对于一个或多个名词短语中的每个，可以确定引用特征表示和先行特征表示，其中引用特征表示包括分布式词表示，并且先行特征表示包括由一个或多个前缀增强的分布式词表示 特征。 在一些实现中，引用特征表示可以由一个或多个引用特征来增强。 可以学习一个或多个名词短语的引用和先行特征表示的核心嵌入。 两个名词短语之间的距离度量可以基于核心嵌入来确定。
-
Patent Agency Ranking
公开(公告)号：US20140279774A1
公开(公告)日：2014-09-18
申请号：US13802462
申请日：2013-03-13
Applicant: Google Inc.
Inventor： Qingzhou Wang , Yu Liang , Ke Yang , Kai Chen
IPC: G06N3/02
CPC classification number: G06N3/04 , G06F3/0484 , G06F17/3053 , G06F17/30707 , G06F17/30864 , G06K9/627 , G06N3/02 , G06N3/0427 , G06N3/084 , G06N7/005
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values using one or more neural network layers to generate an alternative representation of the features, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input using a classifier to generate a respective category score for each category in a pre-determined set of categories, wherein each of the respective category scores measure a predicted likelihood that the resource belongs to the corresponding category.
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，用于使用深层网络评分概念术语。 所述方法之一包括接收包括资源的多个特征的输入，其中每个特征是所述资源的相应属性的值; 使用相应的嵌入功能处理每个特征以生成一个或多个数值; 使用一个或多个神经网络层处理所述数值以产生所述特征的替代表示，其中处理所述浮点值包括对所述浮点值应用一个或多个非线性变换; 以及使用分类器处理所述输入的替代表示以针对预定类别集合中的每个类别生成相应的类别分数，其中各个类别分数中的每一个测量所述资源属于相应类别的预测可能性。
-
公开(公告)号：US11709889B1
公开(公告)日：2023-07-25
申请号：US14853631
申请日：2015-09-14
Applicant: Google Inc.
Inventor： Kai Chen , Steven G. Dropsho , Charles Johan Larsson Tibell , Diego Federici
IPC: G06F16/738 , G06Q30/02 , G06Q30/0251 , G06Q30/0241
CPC classification number: G06F16/738 , G06Q30/0254 , G06Q30/0277
Abstract: In general, in one aspect, a method includes compiling user interaction statistics for a set of content items displayed in association with a first target media document having a non-textual portion, at least some of the content items associated with one or more keywords, based on the interaction statistics, associating the first target media document with at least some of the keywords associated with the content items, and based on a common attribute of the first target media document and a second target media document having a non-textual portion, associating the second target media document with at least some of the keywords assigned to the first target media document. Other aspects include corresponding systems, apparatus, and computer programs stored on computer storage devices.
-
公开(公告)号：US09740680B1
公开(公告)日：2017-08-22
申请号：US14715421
申请日：2015-05-18
Applicant: Google Inc.
Inventor： Tomas Mikolov , Kai Chen , Gregory S. Corrado , Jeffrey A. Dean
CPC classification number: G06F17/2765 , G06F17/2785 , G06N99/005 , G10L15/06
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.
-
公开(公告)号：US20160048754A1
公开(公告)日：2016-02-18
申请号：US14834274
申请日：2015-08-24
Applicant: Google Inc.
Inventor： Qingzhou Wang , Yu Liang , Ke Yang , Kai Chen
IPC: G06N3/04 , G06F17/30 , G06N7/00 , G06F3/0484
CPC classification number: G06N3/04 , G06F3/0484 , G06F17/3053 , G06F17/30707 , G06F17/30864 , G06K9/627 , G06N3/02 , G06N3/0427 , G06N3/084 , G06N7/005
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values using one or more neural network layers to generate an alternative representation of the features, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input using a classifier to generate a respective category score for each category in a pre-determined set of categories, wherein each of the respective category scores measure a predicted likelihood that the resource belongs to the corresponding category.
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，用于使用深层网络评分概念术语。 所述方法之一包括接收包括资源的多个特征的输入，其中每个特征是所述资源的相应属性的值; 使用相应的嵌入功能处理每个特征以生成一个或多个数值; 使用一个或多个神经网络层处理所述数值以产生所述特征的替代表示，其中处理所述浮点值包括对所述浮点值应用一个或多个非线性变换; 以及使用分类器处理所述输入的替代表示以针对预定类别集合中的每个类别生成相应的类别分数，其中各个类别分数中的每一个测量所述资源属于相应类别的预测可能性。
-
公开(公告)号：US20140258005A1
公开(公告)日：2014-09-11
申请号：US14281370
申请日：2014-05-19
Applicant: Google Inc.
Inventor： Rob Kniaz , Abinhay Sharma , Kai Chen , Maxim Drobintsev
IPC: G06Q30/02
CPC classification number: G06Q30/0277 , G06Q30/02 , G06Q30/0201 , G06Q30/0273
Abstract: Advertisements are selected from a plurality of advertisements and associated with an advertisement environment in a document. Document advertisement request code that is configured to issue an advertisement request for one of the selected advertisements for presentation in the advertisement environment is stored in the document.
Abstract translation: 从多个广告中选择广告并且与文档中的广告环境相关联。 文件广告请求代码被配置为发布用于在广告环境中呈现的所选广告之一的广告请求，该文档广告请求代码被存储在文档中。
-
-
-
-
-
-
-
-
-
Search Results
27
records
(took 0.014 seconds)
