Method and apparatus for communications over low bandwidth communications networks
    2.
    发明授权
    Method and apparatus for communications over low bandwidth communications networks 有权
    用于通过低带宽通信网络进行通信的方法和装置

    公开(公告)号:US08805957B2

    公开(公告)日:2014-08-12

    申请号:US13366247

    申请日:2012-02-03

    IPC分类号: G06F15/16

    摘要: A system having a distributed web site is described. The web site is distributed between a client, a server and a web server. The client stores a set of predefined applications that correspond to a part of the web site. The applications are formatted according to a first markup language. From the set of predefined applications, the client can generate queries. The server receives the queries and generates new, related queries. The new queries correspond to a second query protocol. The second query protocol is used by the web server. The web server generates responses to the new queries and sends these responses to the server. The responses are formatted according to a second markup language. These responses correspond to the second portion of the web site. The server then converts the responses into new responses that the client can use.

    摘要翻译: 描述具有分布式网站的系统。 该网站分布在客户端,服务器和Web服务器之间。 客户端存储一组与网站的一部分对应的预定义应用程序。 应用程序根据第一个标记语言进行格式化。 从一组预定义的应用程序,客户端可以生成查询。 服务器接收查询并生成新的相关查询。 新查询对应于第二查询协议。 Web服务器使用第二个查询协议。 Web服务器生成对新查询的响应,并将这些响应发送到服务器。 响应按照第二个标记语言进行格式化。 这些响应对应于网站的第二部分。 然后,服务器将响应转换为客户端可以使用的新响应。

    Spatio-temporal learning algorithms in hierarchical temporal networks
    4.
    发明授权
    Spatio-temporal learning algorithms in hierarchical temporal networks 有权
    分层时间网络中的时空学习算法

    公开(公告)号:US08504494B2

    公开(公告)日:2013-08-06

    申请号:US13227355

    申请日:2011-09-07

    CPC分类号: G06N3/08 G06N3/049

    摘要: A spatio-temporal learning node is a type of HTM node which learns both spatial and temporal groups of sensed input patterns over time. Spatio-temporal learning nodes comprise spatial poolers which are used to determine spatial groups in a set of sensed input patterns. The spatio-temporal learning nodes further comprise temporal poolers which are used to determine groups of sensed input patterns that temporally co-occur. A spatio-temporal learning network is a hierarchical network including a plurality of spatio-temporal learning nodes.

    摘要翻译: 时空学习节点是一种HTM节点,可随时间学习感测输入模式的空间和时间组。 空间学习节点包括用于确定一组感测输入模式中的空间组的空间分组器。 时空学习节点还包括用于确定时间上共同发生的感测输入模式的组的时间分组器。 时空学习网络是包括多个时空学习节点的分层网络。

    Trainable hierarchical memory system and method
    7.
    发明申请
    Trainable hierarchical memory system and method 有权
    可分层记忆系统及方法

    公开(公告)号:US20120109857A1

    公开(公告)日:2012-05-03

    申请号:US13333865

    申请日:2011-12-21

    IPC分类号: G06N5/02

    CPC分类号: G06N3/08

    摘要: Memory networks and methods are provided. Machine intelligence is achieved by a plurality of linked processor units in which child modules receive input data. The input data are processed to identify patterns and/or sequences. Data regarding the observed patterns and/or sequences are passed to a patent module which may receive as inputs data from one or more child modules. the parent module examines its input data for patterns and/or sequences and then provides feedback to the child module or modules regarding the parent-level patterns that correlate with the child-level patterns. These systems and methods are extensible to large networks of interconnected processor modules.

    摘要翻译: 提供内存网络和方法。 机器智能由多个链接的处理器单元实现,其中子模块接收输入数据。 处理输入数据以识别图案和/或序列。 关于观察到的模式和/或序列的数据被传递到可以从一个或多个子模块接收作为输入数据的专利模块。 父模块检查其模式和/或序列的输入数据,然后向子模块或模块提供与子级模式相关的父级模式的反馈。 这些系统和方法可扩展到互连处理器模块的大型网络。

    Method and apparatus for detecting spatial patterns
    8.
    发明授权
    Method and apparatus for detecting spatial patterns 有权
    用于检测空间模式的方法和装置

    公开(公告)号:US07937342B2

    公开(公告)日:2011-05-03

    申请号:US11945919

    申请日:2007-11-27

    IPC分类号: G06E1/00

    CPC分类号: G06N3/049

    摘要: An HTM node learns a plurality of groups of sensed input patterns over time based on the frequency of temporal adjacency of the input patterns. An HTM node receives a new sensed input, the HTM node assigns probabilities as to the likelihood that the new sensed input matches each of the plurality of learned groups. The HTM node then combines this probability distribution (may be normalized) with previous state information to assign probabilities as to the likelihood that the new sensed input is part of each of the learned groups of the HTM node. Then, as described above, the distribution over the set of groups learned by the HTM node is passed to a higher level node. This process is repeated at higher level nodes to infer a cause of the newly sensed input.

    摘要翻译: 基于输入模式的时间邻接的频率,HTM节点随时间学习多个感测输入模式组。 HTM节点接收新的感测输入,HTM节点分配关于新感测输入与多个学习组中的每一个相匹配的可能性的概率。 然后,HTM节点将该概率分布(可以被归一化)与先前的状态信息组合,以便分配关于新感测输入是HTM节点的每个学习组的一部分的可能性的概率。 然后,如上所述,由HTM节点学习的组的分布被传递到较高级节点。 该过程在较高级节点处重复以推断新感测输入的原因。

    Trainable hierarchical memory system and method
    9.
    发明申请
    Trainable hierarchical memory system and method 有权
    可分层记忆系统及方法

    公开(公告)号:US20100191684A1

    公开(公告)日:2010-07-29

    申请号:US12751808

    申请日:2010-03-31

    IPC分类号: G06F15/18 G06N5/02

    CPC分类号: G06N3/08

    摘要: Memory networks and methods are provided. Machine intelligence is achieved by a plurality of linked processor units in which child modules receive input data. The input data are processed to identify patterns and/or sequences. Data regarding the observed patterns and/or sequences are passed to a parent module which may receive as inputs data from one or more child modules. the parent module examines its input data for patterns and/or sequences and then provides feedback to the child module or modules regarding the parent-level patterns that correlate with the child-level patterns. These systems and methods are extensible to large networks of interconnected processor modules.

    摘要翻译: 提供内存网络和方法。 机器智能由多个链接的处理器单元实现,其中子模块接收输入数据。 处理输入数据以识别图案和/或序列。 关于观察到的模式和/或序列的数据被传递给父模块,其可以从一个或多个子模块接收作为输入数据的输入。 父模块检查其模式和/或序列的输入数据,然后向子模块或模块提供与子级模式相关的父级模式的反馈。 这些系统和方法可扩展到互连处理器模块的大型网络。