-
公开(公告)号：US20150161170A1
公开(公告)日：2015-06-11
申请号：US14336692
申请日：2014-07-21
Applicant: Google Inc.
Inventor： Yangli Hector Yee , Samy Bengio , Charles J. Rosenberg , Erik Murphy-Chutorian
CPC classification number: G06F17/30253 , G06F17/30244 , G06F17/30864 , G06K9/4676 , G06K9/6256 , G06K9/66 , G06K2209/01
Abstract: An image classification system trains an image classification model to classify images relative to text appearing with the images. Training images are iteratively selected and classified by the image classification model according to feature vectors of the training images. An independent model is trained for unique n-grams of text. The image classification system obtains text appearing with an image and parses the text into candidate labels for the image. The image classification system determines whether an image classification model has been trained for the candidate labels. When an image classification model corresponding to a candidate label has been trained, the image classification subsystem classifies the image relative to the candidate label. The image is labeled based on candidate labels for which the image is classified as a positive image.
Abstract translation: 图像分类系统训练图像分类模型，以便相对于与图像一起出现的文本来分类图像。 根据训练图像的特征向量，通过图像分类模型迭代地选择和分类训练图像。 对独特的n克文本进行了独立的模型训练。 图像分类系统获得与图像一起出现的文本，并将文本解析为图像的候选标签。 图像分类系统确定是否针对候选标签训练了图像分类模型。 当对应于候选标签的图像分类模型已经被训练时，图像分类子系统将图像相对于候选标签进行分类。 基于将图像分类为正图像的候选标签来标记图像。
-
公开(公告)号：US08787683B1
公开(公告)日：2014-07-22
申请号：US13910493
申请日：2013-06-05
Applicant: Google Inc.
Inventor： Yangli Hector Yee , Samy Bengio , Charles J. Rosenberg , Erik Murphy-Chutorian
CPC classification number: G06F17/30253 , G06F17/30244 , G06F17/30864 , G06K9/4676 , G06K9/6256 , G06K9/66 , G06K2209/01
Abstract: An image classification system trains an image classification model to classify images relative to text appearing with the images. Training images are iteratively selected and classified by the image classification model according to feature vectors of the training images. An independent model is trained for unique n-grams of text. The image classification system obtains text appearing with an image and parses the text into candidate labels for the image. The image classification system determines whether an image classification model has been trained for the candidate labels. When an image classification model corresponding to a candidate label has been trained, the image classification subsystem classifies the image relative to the candidate label. The image is labeled based on candidate labels for which the image is classified as a positive image.
Abstract translation: 图像分类系统训练图像分类模型，以便相对于与图像一起出现的文本来分类图像。 根据训练图像的特征向量，通过图像分类模型迭代地选择和分类训练图像。 对独特的n克文本进行了独立的模型训练。 图像分类系统获得与图像一起出现的文本，并将文本解析为图像的候选标签。 图像分类系统确定是否针对候选标签训练了图像分类模型。 当对应于候选标签的图像分类模型已经被训练时，图像分类子系统将图像相对于候选标签进行分类。 基于将图像分类为正图像的候选标签来标记图像。
-
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：US20170069327A1
公开(公告)日：2017-03-09
申请号：US14846187
申请日：2015-09-04
Applicant: Google Inc.
Inventor： Georg Heigold , Samy Bengio , Ignacio Lopez Moreno
Abstract: This document generally describes systems, methods, devices, and other techniques related to speaker verification, including (i) training a neural network for a speaker verification model, (ii) enrolling users at a client device, and (iii) verifying identities of users based on characteristics of the users' voices. Some implementations include a computer-implemented method. The method can include receiving, at a computing device, data that characterizes an utterance of a user of the computing device. A speaker representation can be generated, at the computing device, for the utterance using a neural network on the computing device. The neural network can be trained based on a plurality of training samples that each: (i) include data that characterizes a first utterance and data that characterizes one or more second utterances, and (ii) are labeled as a matching speakers sample or a non-matching speakers sample.
Abstract translation: 本文件通常描述与扬声器验证相关的系统，方法，设备和其他技术，包括（i）训练用于说话者验证模型的神经网络，（ii）在客户端设备上注册用户，以及（iii）验证用户的身份 基于用户声音的特点。 一些实现包括计算机实现的方法。 该方法可以包括在计算设备处接收表征计算设备的用户的话语的数据。 可以在计算设备处产生使用计算设备上的神经网络的话语的扬声器表示。 可以基于多个训练样本来训练神经网络，每个训练样本：（i）包括表征第一话语的数据和表征一个或多个第二话语的数据，以及（ii）被标记为匹配的说话者样本或非 匹配音箱样品。
-
公开(公告)号：US20150220543A1
公开(公告)日：2015-08-06
申请号：US14687116
申请日：2015-04-15
Applicant: Google Inc.
Inventor： Gal Chechik , Samy Bengio
IPC: G06F17/30
CPC classification number: G06F16/7867 , G06F16/70 , G06F16/738 , G06F16/743 , G06F16/78 , G06F16/783
Abstract: A system, computer readable storage medium, and computer-implemented method presents video search results responsive to a user keyword query. The video hosting system uses a machine learning process to learn a feature-keyword model associating features of media content from a labeled training dataset with keywords descriptive of their content. The system uses the learned model to provide video search results relevant to a keyword query based on features found in the videos. Furthermore, the system determines and presents one or more thumbnail images representative of the video using the learned model.
Abstract translation: 系统，计算机可读存储介质和计算机实现的方法响应于用户关键词查询呈现视频搜索结果。 视频托管系统使用机器学习过程来学习将标记训练数据集中的媒体内容的特征与描述其内容的关键字相关联的特征关键字模型。 该系统使用学习模型，根据视频中的功能提供与关键字查询相关的视频搜索结果。 此外，系统使用所学习的模型来确定并呈现代表视频的一个或多个缩略图。
-
Patent Agency Ranking
公开(公告)号：US20150178596A1
公开(公告)日：2015-06-25
申请号：US14135816
申请日：2013-12-20
Applicant: Google Inc.
Inventor： Samy Bengio , Jeffrey Adgate Dean , Quoc Le , Jonathon Shlens , Yoram Singer
CPC classification number: G06K9/723 , G06K9/00677 , G06K9/6212 , G06K9/72 , G06K2009/6213 , G06N7/005 , G06N99/005
Abstract: Systems and techniques are disclosed for labeling objects within an image. The objects may be labeled by selecting an option from a plurality of options such that each option is a potential label for the object. An option may have an option score associated with. Additionally, a relation score may be calculated for a first option and a second option corresponding to a second object in an image. The relation score may be based on a frequency, probability, or observance corresponding to the co-occurrence of text associated with the first option and the second option in a text corpus such as the World Wide Web. An option may be selected as a label for an object based on a global score calculated based at least on an option score and relation score associated with the option.
Abstract translation: 公开了用于标记图像内的对象的系统和技术。 可以通过从多个选项中选择选项来标记对象，使得每个选项是对象的潜在标签。 选项可能具有与之相关联的选项分数。 另外，可以针对与图像中的第二对象相对应的第一选项和第二选项来计算关系得分。 关系得分可以基于与诸如万维网的文本语料库中与第一选项和第二选项相关联的文本的共现对应的频率，概率或符号。 可以基于至少基于与选项相关联的期权分数和关系分数计算的全局分数来选择对象的标签作为标签。
-
公开(公告)号：US20150161482A1
公开(公告)日：2015-06-11
申请号：US14543312
申请日：2014-11-17
Applicant: Google Inc.
Inventor： Arcot J. Preetham , Thomas J. Duerig , Charles J. Rosenberg , Yangli Hector Yee , Samy Bengio
CPC classification number: G06F17/30675 , G06F17/3028 , G06K9/52 , G06K9/6202 , G06K9/6256 , G06K9/6262 , G06K9/6296 , G06K9/66
Abstract: Methods, systems and apparatus for refining image relevance models. In general, one aspect of the subject matter described in this specification can be implemented in methods that include re-training an image relevance model by generating a first re-trained model based on content feature values of first images of a first portion of training images in a set of training images, receiving, from the first re-trained model, image relevance scores for second images of a second portion of the set of training images, removing, from the set of training images, some of the second images identified as outlier images for which the image relevance score received from the first re-trained model is below a threshold score, and generating a second re-trained model based on content feature values of the first images of the first portion and the second images of the second portion that remain following removal of the outlier images.
Abstract translation: 图像相关模型的方法，系统和装置。 通常，本说明书中描述的主题的一个方面可以以包括通过基于训练图像的第一部分的第一图像的内容特征值生成第一重新训练的模型来重新训练图像相关性模型的方法来实现 在一组训练图像中，从所述第一重新训练的模型中接收所述训练图像集合的第二部分的第二图像的图像相关性分数，从所述训练图像集合中去除被识别为 从第一重新训练的模型接收的图像相关性得分低于阈值分数的异常值图像，并且基于第一部分的第一图像和第二图像的第二图像的内容特征值生成第二重新训练的模型 删除离群图像后仍保留的部分。
-
公开(公告)号：US08965891B1
公开(公告)日：2015-02-24
申请号：US14083043
申请日：2013-11-18
Applicant: Google Inc.
Inventor： Samy Bengio , Gal Chechik , Sergey Ioffe , Jay Yagnik
CPC classification number: G06K9/66 , G06F17/30244 , G06F17/3053 , G06K9/6267 , Y10S707/913 , Y10S707/915
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training scoring models. One method includes storing data identifying a plurality of positive and a plurality of negative training images for a query. The method further includes selecting a first image from either the positive group of images or the negative group of images, and applying a scoring model to the first image. The method further includes selecting a plurality of candidate images from the other group of images, applying the scoring model to each of the candidate images, and then selecting a second image from the candidate images according to scores for the images. The method further includes determining that the scores for the first image and the second image fail to satisfy a criterion, updating the scoring model, and storing the updated scoring model.
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，用于训练评分模型。 一种方法包括存储识别用于查询的多个正训练图像和多个负训练图像的数据。 该方法还包括从图像的正组或负图像组中选择第一图像，以及将评分模型应用于第一图像。 该方法还包括从另一组图像中选择多个候选图像，将评分模型应用于每个候选图像，然后根据图像的分数从候选图像中选择第二图像。 该方法还包括确定第一图像和第二图像的分数不能满足标准，更新评分模型，并存储更新的评分模型。
-
公开(公告)号：US08903182B1
公开(公告)日：2014-12-02
申请号：US13666083
申请日：2012-11-01
Applicant: Google Inc.
Inventor： Thomas J. Duerig , Charles J. Rosenberg , Kunlong Gu , Samy Bengio
CPC classification number: G06F17/30247
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying images. In one aspect, a method includes receiving training samples for a particular data dimension. Each training sample specifies a training value for the data dimension and a measure of relevance between the training sample and a phrase. A value range is determined for the data dimension. The value range is segmented into two or more segments. A predictive model is trained for each segment. The predictive model for each segment is trained to predict an output based on an input value that is within the segment. A classification sample specifying an input value is received. A classification output is computed based on the input value, the predictive model for the segment in which the input value is included, and the predictive model for an adjacent segment.
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，用于分类图像。 一方面，一种方法包括接收特定数据维度的训练样本。 每个训练样本指定数据维度的训练值和训练样本与短语之间的相关性度量。 确定数据维度的值范围。 值范围分为两个或多个段。 对每个细分受训的预测模型。 对每个段的预测模型进行训练，以基于段内的输入值来预测输出。 接收指定输入值的分类样本。 基于输入值，包含输入值的段的预测模型和相邻段的预测模型来计算分类输出。
-
公开(公告)号：US08805812B1
公开(公告)日：2014-08-12
申请号：US13867937
申请日：2013-04-22
Applicant: Google Inc.
Inventor： Gal Chechik , Samy Bengio , Varun Sharma
IPC: G06F17/30
CPC classification number: G06K9/66 , G06F17/30247 , G06F17/30265 , G06K9/6212 , G06K9/6276
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying similar images. In some implementations, a method is provided that includes receiving a collection of images and data associated with each image in the collection of images; generating a sparse feature representation for each image in the collection of images; and training an image similarity function using image triplets sampled from the collection of images and corresponding sparse feature representations.
Abstract translation: 方法，系统和装置，包括编码在计算机存储介质上的用于识别相似图像的计算机程序。 在一些实施方式中，提供了一种方法，其包括接收图像集合中与图像集合中的每个图像相关联的图像和数据的集合; 为图像集合中的每个图像生成稀疏特征表示; 并使用从图像集合和相应的稀疏特征表示中采样的图像三元组训练图像相似度函数。
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.02 seconds)
