中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.023 seconds)

    GENERATING A TRAINING MODEL BASED ON FEEDBACK
    11.
    发明申请
    GENERATING A TRAINING MODEL BASED ON FEEDBACK 审中-公开

    公开(公告)号：US20170091676A1

    公开(公告)日：2017-03-30

    申请号：US15372821

    申请日：2016-12-08

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Liangliang Cao ,  Ning Duan ,  Qian Lin ,  Chen Wang ,  Junchi Yan ,  Xin Zhang

    IPC: G06N99/00

    CPC classification number: G06N5/02 ,  G06N20/00

    Abstract: A method and apparatus for generating a training model based on feedback are provided. The method for generating a training model based on feedback, includes calculating an eigenvector of a sample among a plurality of samples; obtaining scores granted by a user for one or more of the plurality of samples in a round, obtaining scores granted by the user for a first number of samples; obtaining scores granted by the user for a second number of samples in response to detecting, based on the eigenvector, an inconsistency between the scores granted by the user for the first number of samples; and generating a training model based on the scores granted by the user for the first and second numbers of samples. A corresponding apparatus is also provided.

    SEMI-SUPERVISED LEARNING OF WORD EMBEDDINGS
    12.
    发明申请
    SEMI-SUPERVISED LEARNING OF WORD EMBEDDINGS 有权
    半监督的词汇嵌入式学习

    公开(公告)号：US20160329044A1

    公开(公告)日：2016-11-10

    申请号：US14707720

    申请日：2015-05-08

    Applicant: International Business Machines Corporation

    Inventor： Liangliang Cao ,  James J. Fan ,  Chang Wang ,  Bing Xiang ,  Bowen Zhou

    IPC: G10L15/06 ,  G10L15/16 ,  G10L15/18

    CPC classification number: G10L15/063 ,  G06F17/241 ,  G06F17/28 ,  G06F17/3069 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084 ,  G06N3/088 ,  G06N5/022 ,  G06N99/005 ,  G10L15/16 ,  G10L15/18

    Abstract: Software that trains an artificial neural network for generating vector representations for natural language text, by performing the following steps: (i) receiving, by one or more processors, a set of natural language text; (ii) generating, by one or more processors, a set of first metadata for the set of natural language text, where the first metadata is generated using supervised learning method(s); (iii) generating, by one or more processors, a set of second metadata for the set of natural language text, where the second metadata is generated using unsupervised learning method(s); and (iv) training, by one or more processors, an artificial neural network adapted to generate vector representations for natural language text, where the training is based, at least in part, on the received natural language text, the generated set of first metadata, and the generated set of second metadata.

    Abstract translation: 通过执行以下步骤，训练用于生成自然语言文本的矢量表示的人造神经网络的软件：（i）由一个或多个处理器接收一组自然语言文本; （ii）由一个或多个处理器生成用于所述一组自然语言文本的一组第一元数据，其中使用监督学习方法生成所述第一元数据; （iii）由一个或多个处理器生成用于所述一组自然语言文本的一组第二元数据，其中使用无监督学习方法生成所述第二元数据; 以及（iv）由一个或多个处理器训练适于生成自然语言文本的矢量表示的人造神经网络，其中所述训练至少部分地基于所接收的自然语言文本，所生成的第一元数据集合 ，以及所生成的第二元数据集。

    Techniques for Ground-Level Photo Geolocation Using Digital Elevation
    13.
    发明申请
    Techniques for Ground-Level Photo Geolocation Using Digital Elevation 有权

    公开(公告)号：US20140205186A1

    公开(公告)日：2014-07-24

    申请号：US13744688

    申请日：2013-01-18

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Liangliang Cao ,  Noel C.F. Codella ,  Gang Hua ,  John R. Smith

    IPC: G06K9/62

    CPC classification number: G06K9/6256 ,  G06K9/00657

    Abstract: Techniques for generating cross-modality semantic classifiers and using those cross-modality semantic classifiers for ground level photo geo-location using digital elevation are provided. In one aspect, a method for generating cross-modality semantic classifiers is provided. The method includes the steps of: (a) using Geographic Information Service (GIS) data to label satellite images; (b) using the satellite images labeled with the GIS data as training data to generate semantic classifiers for a satellite modality; (c) using the GIS data to label Global Positioning System (GPS) tagged ground level photos; (d) using the GPS tagged ground level photos labeled with the GIS data as training data to generate semantic classifiers for a ground level photo modality, wherein the semantic classifiers for the satellite modality and the ground level photo modality are the cross-modality semantic classifiers.

    GENERATING A TRAINING MODEL BASED ON FEEDBACK
    14.
    发明申请
    GENERATING A TRAINING MODEL BASED ON FEEDBACK 审中-公开
    根据反馈生成培训模型

    公开(公告)号：US20140046893A1

    公开(公告)日：2014-02-13

    申请号：US14055387

    申请日：2013-10-16

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Liangliang Cao ,  Ning Duan ,  Qian Lin ,  Chen Wang ,  Junchi Yan ,  Xin Zhang

    IPC: G06N5/02

    CPC classification number: G06N20/00 ,  G06N5/02

    Abstract: A method and apparatus for generating a training model based on feedback are provided. The method for generating a training model based on feedback, includes calculating an eigenvector of a sample among a plurality of samples; obtaining scores granted by a user for one or more of the plurality of samples in a round, obtaining scores granted by the user for a first number of samples; obtaining scores granted by the user for a second number of samples in response to detecting, based on the eigenvector, an inconsistency between the scores granted by the user for the first number of samples; and generating a training model based on the scores granted by the user for the first and second numbers of samples. A corresponding apparatus is also provided.

    Abstract translation: 提供了一种基于反馈产生训练模型的方法和装置。 基于反馈生成训练模型的方法包括计算多个样本中的样本的特征向量; 获得由用户为一个或多个所述多个样本在一轮中授予的分数，获得由用户为第一数量的样本授予的分数; 响应于基于特征向量检测用户对于第一数量样本所给出的分数之间的不一致性，获得用户对第二数量样本所授予的分数; 以及基于用户为第一和第二数量样本授予的分数生成训练模型。 还提供了相应的装置。

    SYSTEMS AND METHODS FOR INFERRING GENDER BY FUSION OF MULTIMODAL CONTENT
    20.
    发明申请
    SYSTEMS AND METHODS FOR INFERRING GENDER BY FUSION OF MULTIMODAL CONTENT 有权
    通过融合多模态内容感染性别的系统和方法

    公开(公告)号：US20160379086A1

    公开(公告)日：2016-12-29

    申请号：US15226789

    申请日：2016-08-02

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Liangliang Cao ,  Michele Merler ,  John R. Smith

    IPC: G06K9/62 ,  G06K9/32 ,  G06F17/27 ,  G06K9/00 ,  G06N5/04 ,  G06N7/00

    CPC classification number: G06K9/628 ,  G06F17/2785 ,  G06K9/00288 ,  G06K9/00302 ,  G06K9/00362 ,  G06K9/00677 ,  G06K9/325 ,  G06K9/6293 ,  G06N5/04 ,  G06N7/005

    Abstract: A method and systems are provided. A system includes a set of visual and textual classifiers for recognizing semantic concepts in a set of images and assigning semantic scores for the images to predict a gender of a user, and performing gender prediction from visual content and textual content in the images to respectively generate visual-based gender predictions and textual-based gender predictions. The system further includes a multimodal information fusion device for combining, using multimodal information fusion, the visual-based gender predictions, the textual-based gender predictions, and the semantic scores to infer a gender of a user.

    Abstract translation: 提供了一种方法和系统。 系统包括一组视觉和文本分类器，用于识别一组图像中的语义概念，并为图像分配语义分数以预测用户的性别，以及从图像中的视觉内容和文本内容执行性别预测以分别产生 基于视觉的性别预测和基于文本的性别预测。 该系统还包括多模态信息融合装置，用于结合使用多模态信息融合，基于视觉的性别预测，基于文本的性别预测和语义分数来推断用户的性别。

Patent Agency Ranking