DYNAMICALLY ASSIGNING AND EXAMINING SYNAPTIC DELAY
    1.
    发明申请
    DYNAMICALLY ASSIGNING AND EXAMINING SYNAPTIC DELAY 有权
    动态分析和检验SYNAPTIC DELAY

    公开(公告)号:US20150112908A1

    公开(公告)日:2015-04-23

    申请号:US14056856

    申请日:2013-10-17

    CPC classification number: G06N3/08 G06N3/049

    Abstract: A method for dynamically modifying synaptic delays in a neural network includes initializing a delay parameter and operating the neural network. The method further includes dynamically updating the delay parameter based on a program which is based on a statement including the delay parameter.

    Abstract translation: 用于动态修改神经网络中的突触延迟的方法包括初始化延迟参数并操作神经网络。 该方法还包括基于基于包括延迟参数的语句的程序来动态地更新延迟参数。

    TIME SYNCHRONIZATION OF SPIKING NEURON MODELS ON MULTIPLE NODES
    2.
    发明申请
    TIME SYNCHRONIZATION OF SPIKING NEURON MODELS ON MULTIPLE NODES 审中-公开
    SPIKING神经元模型在多个节点上的时间同步

    公开(公告)号:US20150278684A1

    公开(公告)日:2015-10-01

    申请号:US14284275

    申请日:2014-05-21

    CPC classification number: G06N3/049

    Abstract: Certain aspects of the present disclosure support techniques for time synchronization of spiking neuron models that utilize multiple nodes. According to certain aspects, a neural model (e.g., of an artificial nervous system) may be implemented using a plurality of processing nodes, each processing node implementing a neuron model and communicating via the exchange of spike packets carrying information regarding spike information for artificial neurons. A mechanism may be provided for maintaining relative spike-timing between the processing nodes. In some cases, a mechanism may also be provided to alleviate deadlock conditions between the multiple nodes.

    Abstract translation: 本公开的某些方面支持利用多个节点的加标神经元模型的时间同步技术。 根据某些方面,可以使用多个处理节点来实现神经模型(例如,人造神经系统),每个处理节点实施神经元模型并且通过交换携带关于人造神经元的尖峰信息的信息的尖峰分组进行通信 。 可以提供用于在处理节点之间维持相对尖峰定时的机制。 在一些情况下,还可以提供一种机制来减轻多个节点之间的死锁状况。

Patent Agency Ranking