INCREASED DYNAMIC RANGE ARTIFICIAL NEURON NETWORK APPARATUS AND METHODS
    1.
    发明申请
    INCREASED DYNAMIC RANGE ARTIFICIAL NEURON NETWORK APPARATUS AND METHODS 有权
    增加动态范围的人造神经网络设备和方法

    公开(公告)号:US20140379624A1

    公开(公告)日:2014-12-25

    申请号:US13922143

    申请日:2013-06-19

    CPC classification number: G06N3/08 G06N3/049

    Abstract: Apparatus and methods for processing inputs by one or more neurons of a network. The neuron(s) may generate spikes based on receipt of multiple inputs. Latency of spike generation may be determined based on an input magnitude. Inputs may be scaled using for example a non-linear concave transform. Scaling may increase neuron sensitivity to lower magnitude inputs, thereby improving latency encoding of small amplitude inputs. The transformation function may be configured compatible with existing non-scaling neuron processes and used as a plug-in to existing neuron models. Use of input scaling may allow for an improved network operation and reduce task simulation time.

    Abstract translation: 用于由网络的一个或多个神经元处理输入的装置和方法。 基于多个输入的接收,神经元可以产生尖峰。 可以基于输入幅度来确定尖峰生成的延迟。 可以使用例如非线性凹变换来缩放输入。 缩放可以将神经元灵敏度增加到较低幅度的输入,从而改善小振幅输入的延迟编码。 转换函数可以被配置为与现有的非缩放神经元过程兼容,并且用作现有神经元模型的插件。 使用输入缩放可以允许改进的网络操作并减少任务模拟时间。

    APPARATUS AND METHODS FOR PROCESSING INPUTS IN AN ARTIFICIAL NEURON NETWORK
    2.
    发明申请
    APPARATUS AND METHODS FOR PROCESSING INPUTS IN AN ARTIFICIAL NEURON NETWORK 有权
    在人造神经网络中处理输入的装置和方法

    公开(公告)号:US20140379623A1

    公开(公告)日:2014-12-25

    申请号:US13922116

    申请日:2013-06-19

    Abstract: Apparatus and methods for processing inputs by one or more neurons of a network. The neuron(s) may generate spikes based on receipt of multiple inputs. Latency of spike generation may be determined based on an input magnitude. Inputs may be scaled using for example a non-linear concave transform. Scaling may increase neuron sensitivity to lower magnitude inputs, thereby improving latency encoding of small amplitude inputs. The transformation function may be configured compatible with existing non-scaling neuron processes and used as a plug-in to existing neuron models. Use of input scaling may allow for an improved network operation and reduce task simulation time.

    Abstract translation: 用于由网络的一个或多个神经元处理输入的装置和方法。 基于多个输入的接收,神经元可以产生尖峰。 可以基于输入幅度来确定尖峰生成的延迟。 可以使用例如非线性凹变换来缩放输入。 缩放可以将神经元灵敏度增加到较低幅度的输入,从而改善小振幅输入的延迟编码。 转换函数可以被配置为与现有的非缩放神经元过程兼容,并且用作现有神经元模型的插件。 使用输入缩放可以允许改进的网络操作并减少任务模拟时间。

Patent Agency Ranking