Efficient dropout inference for bayesian deep learning

    公开(公告)号:US11410040B2

    公开(公告)日:2022-08-09

    申请号:US16168015

    申请日:2018-10-23

    Abstract: Certain aspects of the present disclosure are directed to methods and apparatus for deep learning in an artificial neural network. One example method generally includes receiving input data at an input to a layer of the neural network; replicating a group of neural processing units in the layer to form a superset of neural processing units, the superset comprising n instances of the group of neural processing units; processing the input data using the superset to generate output data for the layer; and determining an uncertainty of the output data. Processing the input data includes performing a dropout function by zeroing out one or more weights of a set of weights for each of the n instances of the superset of neural processing units and convolving, for each of the n instances in parallel, the input data with one or more non-zeroed out weights of the set of weights.

    ACTIVATING FLASH FOR CAPTURING IMAGES WITH TEXT
    2.
    发明申请
    ACTIVATING FLASH FOR CAPTURING IMAGES WITH TEXT 有权
    用文本捕捉图像的激活闪光

    公开(公告)号:US20160057331A1

    公开(公告)日:2016-02-25

    申请号:US14466659

    申请日:2014-08-22

    Abstract: A method, which is performed by an electronic device, of automatically activating a flash for an image sensor of the electronic device is disclosed. The method may include receiving a first image including at least one text region and determining feature data characterizing the at least one text region in the first image. The method may also identify at least one candidate specular reflection region in the first image. Based on the feature data and the at least one candidate specular reflection region, the flash may be activated. Upon activating the flash, a second image including the at least one text region may be captured.

    Abstract translation: 公开了一种由电子设备执行的用于自动激活电子设备的图像传感器的闪光灯的方法。 该方法可以包括接收包括至少一个文本区域的第一图像和确定表征第一图像中的至少一个文本区域的特征数据。 该方法还可以识别第一图像中的至少一个候选镜面反射区域。 基于特征数据和至少一个候选镜面反射区域,可以激活闪光。 在激活闪光灯时,可以捕获包括至少一个文本区域的第二图像。

    CONTROLLING APPLICATIONS IN MOBILE DEVICE BASED ON ENVIRONMENTAL CONTEXT
    3.
    发明申请
    CONTROLLING APPLICATIONS IN MOBILE DEVICE BASED ON ENVIRONMENTAL CONTEXT 有权
    基于环境条件控制移动设备的应用

    公开(公告)号:US20130252597A1

    公开(公告)日:2013-09-26

    申请号:US13767028

    申请日:2013-02-14

    Abstract: A method for controlling an application in a mobile device is disclosed. The method includes receiving environmental information, inferring an environmental context from the environmental information, and controlling activation of the application based on a set of reference models associated with the inferred environmental context. In addition, the method may include receiving a sound input, extracting a sound feature from the sound input, transmitting the sound feature to a server configured to group a plurality of mobile devices into at least one similar context group, and receiving, from the server, information on a leader device or a non-leader device and the at least one similar context group.

    Abstract translation: 公开了一种用于控制移动设备中的应用的方法。 该方法包括从环境信息中接收环境信息,推断环境背景,以及基于与所推断的环境背景相关联的一组参考模型来控制应用的激活。 此外,该方法可以包括接收声音输入,从声音输入中提取声音特征,将声音特征发送到被配置为将多个移动设备分组成至少一个类似的上下文组的服务器,以及从服务器 关于领导装置或非领导装置的信息以及至少一个类似的上下文组。

    Method and Apparatus for Classifying Data Items Based on Sound Tags
    6.
    发明申请
    Method and Apparatus for Classifying Data Items Based on Sound Tags 审中-公开
    基于声音标签分类数据项的方法和装置

    公开(公告)号:US20150066925A1

    公开(公告)日:2015-03-05

    申请号:US14011437

    申请日:2013-08-27

    CPC classification number: G06F16/683 G06F16/20 G06F16/285

    Abstract: A method for grouping data items in a mobile device is disclosed. In this method, a plurality of data items and a sound tag associated with each of the plurality of data items are stored, and the sound tag includes a sound feature extracted from an input sound indicative of an environmental context for the data item. Further, the method may include generating a new data item, receiving an environmental sound, generating a sound tag associated with the new data item by extracting a sound feature from the environmental sound, and grouping the new data item with at least one of the plurality of data items based on the sound tags associated with the new data item and the plurality of data items.

    Abstract translation: 公开了一种在移动设备中对数据项进行分组的方法。 在该方法中,存储与多个数据项中的每一个相关联的多个数据项和声音标签,声音标签包括从表示数据项目的环境上下文的输入声音中提取的声音特征。 此外,该方法可以包括:生成新数据项,接收环境声音,通过从环境声音提取声音特征来生成与新数据项相关联的声音标记,并且将新数据项与多个 基于与新数据项和多个数据项相关联的声音标记的数据项。

    Emergency handling system using informative alarm sound
    9.
    发明授权
    Emergency handling system using informative alarm sound 有权
    应急处理系统使用信息报警声

    公开(公告)号:US09171450B2

    公开(公告)日:2015-10-27

    申请号:US14012662

    申请日:2013-08-28

    CPC classification number: G08B25/10 H04W4/90

    Abstract: A method includes receiving an alarm sound including information related to an emergency event. The method also includes transmitting, to a server, identification information of the mobile device and the information. The method further includes receiving, from the server, an instruction for responding to the emergency event. The method further includes outputting the instruction.

    Abstract translation: 一种方法包括接收包括与紧急事件相关的信息的警报声音。 该方法还包括向服务器发送移动设备的标识信息和信息。 该方法还包括从服务器接收响应紧急事件的指令。 该方法还包括输出指令。

Patent Agency Ranking