INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS
    1.
    发明申请
    INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS 审中-公开
    使用SPIKING神经网络的图像的不确定对象表示

    公开(公告)号:WO2015148369A3

    公开(公告)日:2015-12-10

    申请号:PCT/US2015021991

    申请日:2015-03-23

    Applicant: QUALCOMM INC

    CPC classification number: G06K9/4623 G06K9/4647 G06K9/6273 G06N3/049 G06N3/10

    Abstract: A method for invariantly representing an object using a spiking neural network includes representing the object by a spike sequence. The method also includes determining a reference feature of the object representation. The method further includes transforming the object representation to a canonical form based on the reference feature.

    Abstract translation: 使用尖峰神经网络不变地表示对象的方法包括通过尖峰序列表示对象。 该方法还包括确定对象表示的参考特征。 该方法还包括基于参考特征将对象表示转换为规范形式。

Patent Agency Ranking