PROBABILISTIC REPRESENTATION OF LARGE SEQUENCES USING SPIKING NEURAL NETWORK
    1.
    发明申请
    PROBABILISTIC REPRESENTATION OF LARGE SEQUENCES USING SPIKING NEURAL NETWORK 审中-公开
    使用SPIKING神经网络的大规模序列的概率表示

    公开(公告)号:US20150278685A1

    公开(公告)日:2015-10-01

    申请号:US14486642

    申请日:2014-09-15

    CPC classification number: G06N3/049 G06N3/0472

    Abstract: A method of using spiking neural network delays to represent sequences includes assigning one or more symbol neurons to each symbol in a dictionary. The method also includes assigning a synapse from each symbol neuron in a group to a particular ngram neuron. A set of synapses associated with the group of symbol neurons comprises a bundle of synapses. In addition, the method includes assigning a delay to each synapse in the bundle. The method further includes representing a symbol sequence based on sequential spiking of symbol neurons and ngram neuron spikes in response to detecting inter event intervals.

    Abstract translation: 使用尖峰神经网络延迟来表示序列的方法包括将一个或多个符号神经元分配给字典中的每个符号。 该方法还包括从组中的每个符号神经元向特定的ngram神经元分配突触。 与该组符号神经元相关联的一组突触包括一组突触。 此外,该方法包括为束中的每个突触分配延迟。 该方法还包括响应于检测到事件间隔而基于符号神经元和ngram神经元峰值的顺序尖峰来表示符号序列。

Patent Agency Ranking