spikingjelly.clock_driven.neuron package

Module contents

class spikingjelly.clock_driven.neuron.BaseNode(v_threshold=1.0, v_reset=0.0, surrogate_function=Sigmoid(alpha=1.0, spiking=True), detach_reset=False, monitor_state=False)[源代码]

基类：torch.nn.modules.module.Module

参数

  • v_threshold – 神经元的阈值电压

  • v_reset – 神经元的重置电压。如果不为 None，当神经元释放脉冲后，电压会被重置为 v_reset； 如果设置为 None，则电压会被减去 v_threshold

  • surrogate_function – 反向传播时用来计算脉冲函数梯度的替代函数

  • detach_reset – 是否将reset过程的计算图分离

  • monitor_state – 是否设置监视器来保存神经元的电压和释放的脉冲。 若为 True，则 self.monitor 是一个字典，键包括 h, v s，分别记录充电后的电压、释放脉冲后的电压、释放的脉冲。 对应的值是一个链表。为了节省显存（内存），列表中存入的是原始变量转换为 numpy 数组后的值。 还需要注意，self.reset() 函数会清空这些链表

可微分SNN神经元的基类神经元。

参数

  • v_threshold – threshold voltage of neurons

  • v_reset – reset voltage of neurons. If not None, voltage of neurons that just fired spikes will be set to v_reset. If None, voltage of neurons that just fired spikes will subtract v_threshold

  • surrogate_function – surrogate function for replacing gradient of spiking functions during back-propagation

  • detach_reset – whether detach the computation graph of reset

  • detach_reset – whether detach the computation graph of reset

  • monitor_state – whether to set a monitor to recode voltage and spikes of neurons. If True, self.monitor will be a dictionary with key h for recording membrane potential after charging, v for recording membrane potential after firing and s for recording output spikes. And the value of the dictionary is lists. To save memory, the elements in lists are numpy array converted from origin data. Besides, self.reset() will clear these lists in the dictionary

This class is the base class of differentiable spiking neurons.

abstract neuronal_charge(dv: torch.Tensor)[源代码]

定义神经元的充电差分方程。子类必须实现这个函数。

Define the charge difference equation. The sub-class must implement this function.

neuronal_fire()[源代码]

根据当前神经元的电压、阈值，计算输出脉冲。

Calculate out spikes of neurons by their current membrane potential and threshold voltage.

neuronal_reset()[源代码]

根据当前神经元释放的脉冲，对膜电位进行重置。

Reset the membrane potential according to neurons’ output spikes.

extra_repr()[源代码]
set_monitor(monitor_state=True)[源代码]
参数

monitor_state – True 或 False，表示开启或关闭monitor

返回

None

设置开启或关闭monitor。

参数

monitor_state – True or False, which indicates turn on or turn off the monitor

返回

None

Turn on or turn off the monitor.

forward(dv: torch.Tensor)[源代码]
参数

dv – 输入到神经元的电压增量

返回

神经元的输出脉冲

按照充电、放电、重置的顺序进行前向传播。

参数

dv – increment of voltage inputted to neurons

返回

out spikes of neurons

Forward by the order of neuronal_charge, neuronal_fire, and neuronal_reset.

reset()[源代码]
返回

None

重置神经元为初始状态，也就是将电压设置为 v_reset。 如果子类的神经元还含有其他状态变量，需要在此函数中将这些状态变量全部重置。

返回

None

Reset neurons to initial states, which means that set voltage to v_reset. Note that if the subclass has other stateful variables, these variables should be reset by this function.

training: bool
class spikingjelly.clock_driven.neuron.IFNode(v_threshold=1.0, v_reset=0.0, surrogate_function=Sigmoid(alpha=1.0, spiking=True), detach_reset=False, monitor_state=False)[源代码]

基类：spikingjelly.clock_driven.neuron.BaseNode

参数

  • v_threshold – 神经元的阈值电压

  • v_reset – 神经元的重置电压。如果不为 None，当神经元释放脉冲后，电压会被重置为 v_reset； 如果设置为 None，则电压会被减去 v_threshold

  • surrogate_function – 反向传播时用来计算脉冲函数梯度的替代函数

  • detach_reset – 是否将reset过程的计算图分离

  • monitor_state – 是否设置监视器来保存神经元的电压和释放的脉冲。 若为 True，则 self.monitor 是一个字典，键包括 h, v s，分别记录充电后的电压、释放脉冲后的电压、释放的脉冲。 对应的值是一个链表。为了节省显存（内存），列表中存入的是原始变量转换为 numpy 数组后的值。 还需要注意，self.reset() 函数会清空这些链表

Integrate-and-Fire 神经元模型，可以看作理想积分器，无输入时电压保持恒定，不会像LIF神经元那样衰减。其阈下神经动力学方程为：

\[\frac{\mathrm{d}V(t)}{\mathrm{d} t} = R_{m}I(t)\]
参数

  • v_threshold – threshold voltage of neurons

  • v_reset – reset voltage of neurons. If not None, voltage of neurons that just fired spikes will be set to v_reset. If None, voltage of neurons that just fired spikes will subtract v_threshold

  • surrogate_function – surrogate function for replacing gradient of spiking functions during back-propagation

  • detach_reset – whether detach the computation graph of reset

  • monitor_state – whether to set a monitor to recode voltage and spikes of neurons. If True, self.monitor will be a dictionary with key h for recording membrane potential after charging, v for recording membrane potential after firing and s for recording output spikes. And the value of the dictionary is lists. To save memory, the elements in lists are numpy array converted from origin data. Besides, self.reset() will clear these lists in the dictionary

The Integrate-and-Fire neuron, which can be seen as a ideal integrator. The voltage of the IF neuron will not decay as that of the LIF neuron. The subthreshold neural dynamics of it is as followed:

\[\frac{\mathrm{d}V(t)}{\mathrm{d} t} = R_{m}I(t)\]
neuronal_charge(dv: torch.Tensor)[源代码]
training: bool
class spikingjelly.clock_driven.neuron.LIFNode(tau=100.0, v_threshold=1.0, v_reset=0.0, surrogate_function=Sigmoid(alpha=1.0, spiking=True), detach_reset=False, monitor_state=False)[源代码]

基类：spikingjelly.clock_driven.neuron.BaseNode

参数

  • tau – 膜电位时间常数。tau 对于这一层的所有神经元都是共享的

  • v_threshold – 神经元的阈值电压

  • v_reset – 神经元的重置电压。如果不为 None，当神经元释放脉冲后，电压会被重置为 v_reset； 如果设置为 None，则电压会被减去 v_threshold

  • surrogate_function – 反向传播时用来计算脉冲函数梯度的替代函数

  • detach_reset – 是否将reset过程的计算图分离

  • monitor_state – 是否设置监视器来保存神经元的电压和释放的脉冲。 若为 True，则 self.monitor 是一个字典，键包括 h, v s，分别记录充电后的电压、释放脉冲后的电压、释放的脉冲。 对应的值是一个链表。为了节省显存（内存），列表中存入的是原始变量转换为 numpy 数组后的值。 还需要注意，self.reset() 函数会清空这些链表

Leaky Integrate-and-Fire 神经元模型，可以看作是带漏电的积分器。其阈下神经动力学方程为：

\[\tau_{m} \frac{\mathrm{d}V(t)}{\mathrm{d}t} = -(V(t) - V_{reset}) + R_{m}I(t)\]
参数

  • tau – membrane time constant. tau is shared by all neurons in this layer

  • v_threshold – threshold voltage of neurons

  • v_reset – reset voltage of neurons. If not None, voltage of neurons that just fired spikes will be set to v_reset. If None, voltage of neurons that just fired spikes will subtract v_threshold

  • surrogate_function – surrogate function for replacing gradient of spiking functions during back-propagation

  • detach_reset – whether detach the computation graph of reset

  • monitor_state – whether to set a monitor to recode voltage and spikes of neurons. If True, self.monitor will be a dictionary with key h for recording membrane potential after charging, v for recording membrane potential after firing and s for recording output spikes. And the value of the dictionary is lists. To save memory, the elements in lists are numpy array converted from origin data. Besides, self.reset() will clear these lists in the dictionary

The Leaky Integrate-and-Fire neuron, which can be seen as a leaky integrator. The subthreshold neural dynamics of it is as followed:

\[\tau_{m} \frac{\mathrm{d}V(t)}{\mathrm{d}t} = -(V(t) - V_{reset}) + R_{m}I(t)\]
extra_repr()[源代码]
neuronal_charge(dv: torch.Tensor)[源代码]
training: bool