专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明授权

US09514404B1 Using embedding functions with a deep network 有权
公开(公告)号：US09514404B1
公开(公告)日：2016-12-06
申请号：US14860497
申请日：2015-09-21
申请人： Google Inc.
发明人： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Gary R. Holt , Julian P. Grady , Sharat Chikkerur , David W. Sculley, II
IPC分类号： G06F15/18 , G06E1/00 , G06E3/00 , G06G7/00 , G06N3/08 , G06N3/04
CPC分类号： G06N3/08 , G06N3/04 , G06N3/0454 , G06N3/084
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. One of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.

22. 发明授权

US09477930B2 Cross channel optimization systems and methods 有权
公开(公告)号：US09477930B2
公开(公告)日：2016-10-25
申请号：US13784397
申请日：2013-03-04
申请人： ACCENTURE GLOBAL SERVICES LIMITED
发明人： Hikaru Phillips
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00 , G06N3/02 , G06N99/00 , G06Q30/02 , G06N3/063 , G06N3/04
CPC分类号： G06N99/005 , G06N3/02 , G06N3/0454 , G06N3/049 , G06N3/063 , G06Q30/02
摘要： The inventive subject matter is generally directed to a cross channel optimization system, methods, and related software which provide for the conducting of experiments and/or optimization of digital content across a plurality of external content systems to user of the external content systems.

23. 发明授权

US09384196B2 Signature generation for multimedia deep-content-classification by a large-scale matching system and method thereof 有权
标题翻译：通过大规模匹配系统进行多媒体深度内容分类的签名生成及其方法
公开(公告)号：US09384196B2
公开(公告)日：2016-07-05
申请号：US14619767
申请日：2015-02-11
申请人： Cortica, Ltd.
发明人： Igal Raichelgauz , Karina Odinaev , Yehoshua Y. Zeevi
IPC分类号： G06F15/00 , G06E1/00 , G06E3/00 , G06F17/30 , G06K9/00 , G10L15/26 , G10L25/54 , G10L15/32 , G10L15/06 , G10L13/06
CPC分类号： G06F17/30746 , G06F17/30017 , G06F17/3002 , G06F17/30312 , G06F17/30595 , G06F17/30598 , G06F17/30743 , G06F17/30749 , G06F17/30778 , G06F17/30787 , G06F17/30796 , G06F17/30799 , G06K9/00744 , G10L13/06 , G10L15/063 , G10L15/26 , G10L15/32 , G10L25/54 , G10L25/57
摘要： A method and system for generating a large-scale database of heterogeneous speech are provided. The method includes transcribing a plurality of multimedia signals retrieved from a large text database and a speech database; randomly selecting a plurality of speech segments from the plurality of multimedia signals, wherein each speech segment of the plurality of speech segments is of a random length; generating a plurality of signatures based on the plurality of speech segments; and populating the large-scale database with the plurality of signatures respective of the plurality of multimedia signals.
摘要翻译：提供了一种用于生成异构语音的大规模数据库的方法和系统。该方法包括转录从大文本数据库和语音数据库检索的多个多媒体信号; 从所述多个多媒体信号中随机选择多个语音片段，其中所述多个语音片段中的每个语音片段具有随机长度; 基于所述多个语音段生成多个签名; 以及利用所述多个多媒体信号中的多个签名填充所述大规模数据库。

24. 发明授权

US09355367B2 System and method for using graph transduction techniques to make relational classifications on a single connected network 有权
标题翻译：使用图形转换技术在单个连接网络上进行关系分类的系统和方法
公开(公告)号：US09355367B2
公开(公告)日：2016-05-31
申请号：US13787807
申请日：2013-03-07
申请人： International Business Machines Corporation
发明人： Amit Dhurandhar , Jun Wang
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00 , G06N99/00 , G06N3/08 , G06N5/02
CPC分类号： G06N99/005 , G06F17/30958 , G06N3/08 , G06N5/022 , G06N7/00
摘要： A system and method for extending partially labeled data graphs to unlabeled nodes in a single network classification by weighting the data with a weight matrix that uses a modified graph Laplacian based regularization framework and applying graph transduction methods to the weighted data. The technique may be applied to data graphs that are directed or undirected, that may or may not have attributes and that may be homogeneous or heterogeneous.
摘要翻译：通过用权重矩阵对数据进行加权来将部分标记的数据图形扩展到未标记的节点的系统和方法，该权重矩阵使用基于拉普拉斯算子的经修正的正则化框架，并将图形转换方法应用于加权数据。该技术可以应用于有向或无向的数据图，其可以具有或可以不具有属性并且可以是均匀的或异质的。

25. 发明授权

US09269050B2 Classification using correntropy 有权
标题翻译：使用科学分类
公开(公告)号：US09269050B2
公开(公告)日：2016-02-23
申请号：US13811317
申请日：2011-07-22
申请人： Jose Carlos Principe , Abhishek Singh
发明人： Jose Carlos Principe , Abhishek Singh
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00 , G06N7/00 , G06K9/62
CPC分类号： G06N7/00 , G06K9/6215
摘要： Various methods and systems are provided for classification using correntropy. In one embodiment, a classifying device includes a processing unit and memory storing instructions in modules that when executed by the processing unit cause the classifying device to adaptively classify a data value using a correntropy loss function. In another embodiment, a method includes adjusting a weight of a classifier based at least in part on a change in a correntropy loss function signal and classifying a data value using the classifier. In another embodiment, a method includes classifying a data value by predicting a label for the data value using a discriminant function, determining a correntopy statistical similarity between the predicted label and an actual label based at least in part on a correntropy loss function, and minimizing an expected risk associated with the predicted label based at least in part on a correntropy statistical similarity.
摘要翻译：提供了各种方法和系统，用于使用correntropy进行分类。在一个实施例中，分类装置包括处理单元和在模块中存储指令的存储器，当处理单元执行时，使得分类装置使用科学损失函数自适应地对数据值进行分类。在另一个实施例中，一种方法包括至少部分地基于科学损失函数信号的变化调整分类器的权重，并使用分类器对数据值进行分类。在另一个实施例中，一种方法包括通过使用判别函数预测数据值的标签来分类数据值，至少部分地基于科学损失函数确定预测标签和实际标签之间的对应统计学相似度，并且最小化至少部分地基于科学统计学相似性与预测标签相关联的预期风险。

26. 发明授权

US09104975B2 Memristor apparatus 有权
标题翻译：忆阻器
公开(公告)号：US09104975B2
公开(公告)日：2015-08-11
申请号：US13421398
申请日：2012-03-15
申请人： Alex Nugent
发明人： Alex Nugent
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00 , G06N3/063 , H03K19/00
CPC分类号： G06N3/063 , H03K19/00
摘要： A memristor apparatus comprising a plurality of meta-stable switching elements.
摘要翻译：一种忆阻器装置，包括多个元稳定的开关元件。

27. 发明授权

US09081763B2 Ranking in cascading learning system 有权
标题翻译：级联学习系统排名
公开(公告)号：US09081763B2
公开(公告)日：2015-07-14
申请号：US13653161
申请日：2012-10-16
申请人： SAP SE
发明人： Robert Heidasch
IPC分类号： G06F15/18 , G06E1/00 , G06E3/00 , G06G7/00 , G06F17/27 , G06F17/30
CPC分类号： G06F17/2785 , G06F17/30731
摘要： A ranking in cascading learning system is described. The cascading learning system has a request analyzer, a request dispatcher and classifier, a search module, a terminology manager, and a cluster manager. The request analyzer receives a request for search terms from a client application and determines term context in the request to normalize request data from the term context. The normalized request data are classified and dispatched to a corresponding domain-specific module with a request dispatcher ranking calibrator. Each domain-specific module of a search module generates a prediction with a trained probability of an expected output using a corresponding domain-specific ranking calibrator. The terminology manager receives normalized request data from the request dispatcher and classifier, and manages terminology stored in a contextual network. The cluster manager comprises a central ranking calibrator, a training and sot container, and a module generator configured to generate a pluggable module.
摘要翻译：描述了级联学习系统的排名。级联学习系统具有请求分析器，请求分派器和分类器，搜索模块，术语管理器和集群管理器。请求分析器从客户端应用程序接收关于搜索项的请求，并确定请求中的术语上下文以使术语上下文中的请求数据正常化。归一化的请求数据被分类并分配给具有请求分派器等级校准器的相应的域特定模块。搜索模块的每个域特定模块使用相应的域特定排序校准器来生成预期输出的训练概率的预测。术语管理器从请求分派器和分类器接收归一化的请求数据，并管理存储在上下文网络中的术语。集群管理器包括中央排列校准器，训练和容器，以及被配置为生成可插拔模块的模块发生器。

28. 发明授权

US09020868B2 Distributed analytics method for creating, modifying, and deploying software pneurons to acquire, review, analyze targeted data 有权
标题翻译：分布式分析方法，用于创建，修改和部署软件派对，以获取，审查，分析目标数据
公开(公告)号：US09020868B2
公开(公告)日：2015-04-28
申请号：US13713624
申请日：2012-12-13
申请人： Pneuron Corp.
发明人： Elizabeth Winters Elkins , Douglas Wiley Bachelor , Simon Byford Moss , Thomas C. Fountain , Raul Hugo Curbelo
IPC分类号： G06E1/00 , G06N5/02
CPC分类号： G06N5/02 , G06N5/022
摘要： A method and system for the integration of disparate data stored within an Information Technology infrastructure of a company is provided. The system and method enables holistic, real time control of data discovery, retrieval and analysis. The system combines data mining, retrieval and analytics at the source of the data, thereby solving traditional problems with disparate and distributed data, systems, business processes and analytics across an organization. The system enables a user to configure and target data, then apply rules, workflows and analytics from one central source. This process is accomplished by distributing functions in the form of software pneurons against the existing infrastructure for maximum processing while preserving a robust and extendable suite of definitions. The system uses the existing application, network and hardware assets and enables connection to the native data, maps only the data fields that need to be mapped to carry out the desired analysis, runs the analysis and then returns the data to a central location to be assembled, analyzed, organized and/or reported.
摘要翻译：提供了存储在公司信息技术基础设施中的不同数据的集成方法和系统。该系统和方法可实现数据发现，检索和分析的全面实时控制。该系统将数据挖掘，检索和分析结合在一起，从而解决了跨组织不同和分布式数据，系统，业务流程和分析的传统问题。该系统使用户能够配置和定位数据，然后从一个中心来源应用规则，工作流和分析。这个过程是通过以现有基础设施的形式分配函数来实现的，以最大限度地处理这些功能，同时保持一个强大而可扩展的定义。系统使用现有的应用程序，网络和硬件资产，并连接到本机数据，仅映射需要映射的数据字段进行所需的分析，运行分析，然后将数据返回到中心位置组装，分析，组织和/或报告。

29. 发明授权

US08990130B2 Consolidating multiple neurosynaptic cores into one memory 有权
标题翻译：巩固多个神经突触核心到一个记忆体
公开(公告)号：US08990130B2
公开(公告)日：2015-03-24
申请号：US13683234
申请日：2012-11-21
申请人： International Business Machines Corporation
发明人： Rodrigo Alvarez-Icaza Rivera , John V. Arthur , Andrew S. Cassidy , Paul A. Merolla , Dharmendra S. Modha
IPC分类号： G06F15/18 , G06E1/00 , G06E3/00 , G06G7/00 , G06N3/02 , G06N3/04 , G06N3/063
CPC分类号： G06N3/04 , G06N3/063
摘要： Embodiments of the invention relate to a neural network system comprising a single memory block for multiple neurosynaptic core modules. One embodiment comprises a neural network system including a memory array that maintains information for multiple neurosynaptic core modules. Each neurosynaptic core module comprises multiple neurons. The neural network system further comprises at least one logic circuit. Each logic circuit receives neuronal firing events targeting a neurosynaptic core module of the neural network system, and said logic circuit integrates the firing events received based on information maintained in said memory for said neurosynaptic core module.
摘要翻译：本发明的实施例涉及包括用于多个神经突触核心模块的单个存储块的神经网络系统。一个实施例包括神经网络系统，其包括维持多个神经突触核心模块的信息的存储器阵列。每个神经突触核心模块包括多个神经元。神经网络系统还包括至少一个逻辑电路。每个逻辑电路接收针对神经网络系统的神经突触核心模块的神经元触发事件，并且所述逻辑电路基于所述神经突触核心模块的所述存储器中保存的信息来集成所接收的触发事件。

30. 发明授权

US08983885B1 Prospective media content generation using neural network modeling 有权
标题翻译：使用神经网络建模的前瞻性媒体内容生成
公开(公告)号：US08983885B1
公开(公告)日：2015-03-17
申请号：US13609141
申请日：2012-09-10
申请人： Meghana Bhatt , Rachel Payne
发明人： Meghana Bhatt , Rachel Payne
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00 , G06N99/00
CPC分类号： G06N3/02 , G06F17/16 , G06N99/005
摘要： A system for prospectively identifying media characteristics for inclusion in media content is disclosed. A neural network database including media characteristic information and feature information may associate relationships among the media characteristic information and feature information. Personal characteristic information associated with target media consumers may be used to select a subset of the neural network database. A first set of nodes, representing selected feature information, may be activated. The node interactions may be calculated to detect the activation of a second set of nodes, the second set of nodes representing media characteristic information. Generally, a node is activated when an activation value of the node exceeds a threshold value. Media characteristic information may be identified for inclusion in media content based on the second set of nodes.
摘要翻译：公开了一种用于前瞻性地识别媒体内容的媒体特征的系统。包括媒体特征信息和特征信息的神经网络数据库可以关联媒体特征信息和特征信息之间的关系。可以使用与目标媒体消费者相关联的个人特征信息来选择神经网络数据库的子集。可以激活表示所选特征信息的第一组节点。可以计算节点交互以检测第二组节点的激活，第二组节点表示媒体特征信息。通常，当节点的激活值超过阈值时，节点被激活。可以基于第二组节点来识别媒体特征信息以包含在媒体内容中。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式