EVENT-BASED INFERENCE AND LEARNING FOR STOCHASTIC SPIKING BAYESIAN NETWORKS
    1.
    发明申请
    EVENT-BASED INFERENCE AND LEARNING FOR STOCHASTIC SPIKING BAYESIAN NETWORKS 审中-公开
    基于事件的干预和学习用于STOCHASTIC SPIKING BAYESIAN网络

    公开(公告)号:US20150242745A1

    公开(公告)日:2015-08-27

    申请号:US14281220

    申请日:2014-05-19

    CPC classification number: G06N3/08 G06N3/049 G06N7/005

    Abstract: A method of performing event-based Bayesian inference and learning includes receiving input events at each node. The method also includes applying bias weights and/or connection weights to the input events to obtain intermediate values. The method further includes determining a node state based on the intermediate values. Further still, the method includes computing an output event rate representing a posterior probability based on the node state to generate output events according to a stochastic point process.

    Abstract translation: 执行基于事件的贝叶斯推理和学习的方法包括在每个节点处接收输入事件。 该方法还包括将偏置权重和/或连接权重应用于输入事件以获得中间值。 该方法还包括基于中间值来确定节点状态。 此外,该方法还包括基于节点状态计算表示后验概率的输出事件速率,以根据随机点处理生成输出事件。

Patent Agency Ranking