中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.014 seconds)

    Generating labeled images
    2.
    发明授权
    Generating labeled images 有权
    生成标记图像

    公开(公告)号：US09256807B1

    公开(公告)日：2016-02-09

    申请号：US13803642

    申请日：2013-03-14

    Applicant: Google Inc.

    Inventor： Jonathon Shlens ,  Quoc V. Le ,  Gregory S. Corrado ,  Marc'Aurelio Ranzato

    IPC: G06K9/62 ,  G06F17/30

    CPC classification number: G06K9/627 ,  G06F17/30244 ,  G06F17/30247 ,  G06F17/30268 ,  G06F17/3079 ,  G06F17/30843 ,  G06K9/6215 ,  G06K9/6255 ,  G06K9/6256

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating labeled images. One of the methods includes selecting a plurality of candidate videos from videos identified in a response to a search query derived from a label for an object category; selecting one or more initial frames from each of the candidate videos; detecting one or more initial images of objects in the object category in the initial frames; for each initial frame including an initial image of an object in the object category, tracking the object through surrounding frames to identify additional images of the object; and selecting one or more images from the one or more initial images and one or more additional images as database images of objects belonging to the object 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，用于生成标记图像。 方法之一包括从对于从对象类别的标签导出的搜索查询的响应中识别的视频中选择多个候选视频; 从每个候选视频中选择一个或多个初始帧; 检测初始帧中对象类别中的对象的一个​​或多个初始图像; 对于包括对象类别中的对象的初始图像的每个初始帧，通过周围帧跟踪对象以识别对象的附加图像; 以及从一个或多个初始图像和一个或多个附加图像中选择一个或多个图像作为属于对象类别的对象的数据库图像。

    GENERATING REPRESENTATIONS OF INPUT SEQUENCES USING NEURAL NETWORKS
    3.
    发明申请
    GENERATING REPRESENTATIONS OF INPUT SEQUENCES USING NEURAL NETWORKS 审中-公开
    使用神经网络生成输入序列的表示

    公开(公告)号：US20150356401A1

    公开(公告)日：2015-12-10

    申请号：US14731326

    申请日：2015-06-04

    Applicant: Google Inc.

    Inventor： Oriol Vinyals ,  Quoc V. Le ,  Ilya Sutskever

    IPC: G06N3/02

    CPC classification number: G06N3/02 ,  G06F17/28 ,  G06N3/0445 ,  G06N3/0454

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representations of input sequences. One of the methods includes obtaining an input sequence, the input sequence comprising a plurality of inputs arranged according to an input order; processing the input sequence using a first long short term memory (LSTM) neural network to convert the input sequence into an alternative representation for the input sequence; and processing the alternative representation for the input sequence using a second LSTM neural network to generate a target sequence for the input sequence, the target sequence comprising a plurality of outputs arranged according to an output order.

    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，用于产生输入序列的表示。 所述方法之一包括获得输入序列，所述输入序列包括根据输入顺序排列的多个输入; 使用第一长的短期存储器（LSTM）神经网络来处理输入序列，以将输入序列转换成输入序列的替代表示; 以及使用第二LSTM神经网络处理所述输入序列的替代表示，以生成所述输入序列的目标序列，所述目标序列包括根据输出顺序排列的多个输出。

    PREDICTING A SEARCH ENGINE RANKING SIGNAL VALUE
    4.
    发明申请
    PREDICTING A SEARCH ENGINE RANKING SIGNAL VALUE 审中-公开

    公开(公告)号：US20180157758A1

    公开(公告)日：2018-06-07

    申请号：US15369849

    申请日：2016-12-05

    Applicant: Google Inc.

    Inventor： Javier Spagnolo Arrizabalaga ,  Malte Nuhn ,  Quoc V. Le ,  Daniel Duckworth ,  Matthias Heiler

    IPC: G06F17/30 ,  G06N3/08

    CPC classification number: G06F17/30867 ,  G06F17/30861 ,  G06F17/3089 ,  G06N3/08

    Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for augmenting search engine index that indexes resources from a collection of resources. In one aspect, a method of augmenting a first search engine index that indexes resources from a first collection of resources includes the actions of identifying a first resource, in the first collection of resources, that is indexed in the first search engine index for which a value of a search engine ranking signal is not available, wherein a search engine uses values of the search engine ranking signal in ranking resources in response to received search queries; processing text from the first resource using a machine learning model, the machine learning model being configured to: process the text to predict a value of the search engine ranking signal for the first resource; and updating the first search engine index by associating the predicted value of the search engine ranking signal with the first resource in the first search engine index.

    Speech recognition with attention-based recurrent neural networks
    5.
    发明授权
    Speech recognition with attention-based recurrent neural networks 有权

    公开(公告)号：US09990918B1

    公开(公告)日：2018-06-05

    申请号：US15788300

    申请日：2017-10-19

    Applicant: Google Inc.

    Inventor： William Chan ,  Navdeep Jaitly ,  Quoc V. Le ,  Oriol Vinyals ,  Noam M. Shazeer

    IPC: G10L15/16 ,  G06F17/22 ,  G10L15/183 ,  G10L15/26

    CPC classification number: G10L15/16

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

    Speech recognition with attention-based recurrent neural networks
    6.
    发明授权
    Speech recognition with attention-based recurrent neural networks 有权

    公开(公告)号：US09799327B1

    公开(公告)日：2017-10-24

    申请号：US15055476

    申请日：2016-02-26

    Applicant: Google Inc.

    Inventor： William Chan ,  Navdeep Jaitly ,  Quoc V. Le ,  Oriol Vinyals ,  Noam M. Shazeer

    IPC: G10L15/16 ,  G10L15/26 ,  G06F17/22 ,  G10L15/183

    CPC classification number: G10L15/16

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

    GENERATING VECTOR REPRESENTATIONS OF DOCUMENTS
    7.
    发明申请
    GENERATING VECTOR REPRESENTATIONS OF DOCUMENTS 审中-公开
    生成文档的矢量表示

    公开(公告)号：US20150220833A1

    公开(公告)日：2015-08-06

    申请号：US14609869

    申请日：2015-01-30

    Applicant: Google Inc.

    Inventor： Quoc V. Le

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06F16/583 ,  G06F17/277 ,  G06N3/04 ,  G06N3/084

    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; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system has been trained to receive an input document and a sequence of words from the input document and to generate a respective word score for each word in a set of words, wherein each of the respective word scores represents a predicted likelihood that the corresponding word follows a last word in the sequence in the input document, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of sequences of words to the trained neural network system to determine the vector representation for the new document using gradient descent.

    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，用于生成文档向量表示。 其中一种方法包括获得新文件; 以及使用经过训练的神经网络系统确定新文档的向量表示，其中所训练的神经网络系统已被训练以从输入文档接收输入文档和单词序列，并且为每个单词生成相应的单词分数 一组单词，其中各个单词分数中的每一个表示对应单词遵循输入文档中的序列中的最后一个单词的预测似然性，并且其中使用经过训练的神经网络系统确定新文档的向量表示包括迭代地 将所述多个单词序列中的每一个提供给所训练的神经网络系统，以使用梯度下降来确定所述新文档的向量表示。

    LABEL CONSISTENCY FOR IMAGE ANALYSIS
    8.
    发明申请
    LABEL CONSISTENCY FOR IMAGE ANALYSIS 审中-公开

    公开(公告)号：US20170220906A1

    公开(公告)日：2017-08-03

    申请号：US15488041

    申请日：2017-04-14

    Applicant: Google Inc.

    Inventor： Samy Bengio ,  Jeffrey Adgate Dean ,  Quoc V. Le ,  Jonathon Shlens ,  Yoram Singer

    IPC: G06K9/72 ,  G06K9/62

    CPC classification number: G06K9/723 ,  G06K9/00677 ,  G06K9/6212 ,  G06K9/72 ,  G06K2009/6213 ,  G06N7/005 ,  G06N20/00

    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.

    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS
    10.
    发明申请
    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS 审中-公开

    公开(公告)号：US20180129972A1

    公开(公告)日：2018-05-10

    申请号：US15394708

    申请日：2016-12-29

    Applicant: Google Inc.

    Inventor： Zhifeng Chen ,  Michael Schuster ,  Melvin Jose Johnson Premkumar ,  Yonghui Wu ,  Quoc V. Le ,  Maxim Krikun ,  Thorsten Brants

    IPC: G06N99/00 ,  G06F17/28

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.

Patent Agency Ranking