spikingjelly.activation_based.learning module#

spikingjelly.activation_based.learning.stdp_linear_single_step(fc, in_spike, out_spike, trace_pre, trace_post, tau_pre, tau_post, f_pre=<function <lambda>>, f_post=<function <lambda>>)[源代码]#

API Language - 中文 | English

  • 中文

对单步脉冲输入执行全连接层的 STDP 更新，返回更新后的 pre/post trace 与权重增量。

参数:

  • fc (Linear) -- 需要执行 STDP 的全连接层

  • in_spike (Tensor) -- 输入脉冲，shape = [batch_size, in_features]

  • out_spike (Tensor) -- 输出脉冲，shape = [batch_size, out_features]

  • trace_pre (Union[float, Tensor, None]) -- pre-synaptic trace。若为 None，则使用标量 0.0 初始化

  • trace_post (Union[float, Tensor, None]) -- post-synaptic trace。若为 None，则使用标量 0.0 初始化

  • tau_pre (float) -- pre trace 的时间常数，要求为正数

  • tau_post (float) -- post trace 的时间常数，要求为正数

  • f_pre (Callable) -- 作用在当前权重上的 pre-update 调制函数

  • f_post (Callable) -- 作用在当前权重上的 post-update 调制函数

返回:

(trace_pre, trace_post, delta_w)，其中 delta_w 的形状与 fc.weight 相同

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

  • English

Apply one STDP update step to a linear layer driven by single-step spike inputs, and return the updated pre/post traces together with the weight increment.

参数:

  • fc (Linear) -- Linear layer updated by STDP

  • in_spike (Tensor) -- Input spikes with shape = [batch_size, in_features]

  • out_spike (Tensor) -- Output spikes with shape = [batch_size, out_features]

  • trace_pre (Union[float, Tensor, None]) -- Pre-synaptic trace. If None, it is initialized as scalar 0.0

  • trace_post (Union[float, Tensor, None]) -- Post-synaptic trace. If None, it is initialized as scalar 0.0

  • tau_pre (float) -- Time constant of the pre trace. Expected to be positive

  • tau_post (float) -- Time constant of the post trace. Expected to be positive

  • f_pre (Callable) -- Pre-update modulation function applied to the current weight

  • f_post (Callable) -- Post-update modulation function applied to the current weight

返回:

(trace_pre, trace_post, delta_w), where delta_w has the same shape as fc.weight

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

spikingjelly.activation_based.learning.mstdp_linear_single_step(fc, in_spike, out_spike, trace_pre, trace_post, tau_pre, tau_post, f_pre=<function <lambda>>, f_post=<function <lambda>>)[源代码]#

API Language - 中文 | English

  • 中文

对单步脉冲输入执行全连接层的 reward-modulated STDP eligibility 计算。

参数:

  • fc (Linear) -- 需要执行 mSTDP 的全连接层

  • in_spike (Tensor) -- 输入脉冲，shape = [batch_size, in_features]

  • out_spike (Tensor) -- 输出脉冲，shape = [batch_size, out_features]

  • trace_pre (Union[float, Tensor, None]) -- pre-synaptic trace。若为 None，则使用标量 0.0 初始化

  • trace_post (Union[float, Tensor, None]) -- post-synaptic trace。若为 None，则使用标量 0.0 初始化

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

返回:

(trace_pre, trace_post, eligibility)，其中 eligibility 的形状为 [batch_size, out_features, in_features]

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

  • English

Compute the reward-modulated STDP eligibility tensor for a linear layer under single-step spike inputs.

参数:

  • fc (Linear) -- Linear layer updated by mSTDP

  • in_spike (Tensor) -- Input spikes with shape = [batch_size, in_features]

  • out_spike (Tensor) -- Output spikes with shape = [batch_size, out_features]

  • trace_pre (Union[float, Tensor, None]) -- Pre-synaptic trace. If None, it is initialized as scalar 0.0

  • trace_post (Union[float, Tensor, None]) -- Post-synaptic trace. If None, it is initialized as scalar 0.0

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

返回:

(trace_pre, trace_post, eligibility), where eligibility has shape [batch_size, out_features, in_features]

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

spikingjelly.activation_based.learning.mstdpet_linear_single_step(fc, in_spike, out_spike, trace_pre, trace_post, tau_pre, tau_post, tau_trace, f_pre=<function <lambda>>, f_post=<function <lambda>>)[源代码]#

API Language - 中文 | English

  • 中文

对单步脉冲输入执行全连接层的 mSTDP-ET eligibility 计算。

参数:

  • fc (Linear) -- 需要执行 mSTDP-ET 的全连接层

  • in_spike (Tensor) -- 输入脉冲，shape = [in_features]

  • out_spike (Tensor) -- 输出脉冲，shape = [out_features]

  • trace_pre (Union[float, Tensor, None]) -- pre-synaptic trace。若为 None，则使用标量 0.0 初始化

  • trace_post (Union[float, Tensor, None]) -- post-synaptic trace。若为 None，则使用标量 0.0 初始化

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • tau_trace (float) -- eligibility trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

返回:

(trace_pre, trace_post, eligibility)，其中 eligibility 的形状与 fc.weight 相同

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

  • English

Compute the mSTDP-ET eligibility update for a linear layer under single-step spike inputs.

参数:

  • fc (Linear) -- Linear layer updated by mSTDP-ET

  • in_spike (Tensor) -- Input spikes with shape = [in_features]

  • out_spike (Tensor) -- Output spikes with shape = [out_features]

  • trace_pre (Union[float, Tensor, None]) -- Pre-synaptic trace. If None, it is initialized as scalar 0.0

  • trace_post (Union[float, Tensor, None]) -- Post-synaptic trace. If None, it is initialized as scalar 0.0

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • tau_trace (float) -- Time constant of the eligibility trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

返回:

(trace_pre, trace_post, eligibility), where eligibility has the same shape as fc.weight

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

spikingjelly.activation_based.learning.stdp_conv2d_single_step(conv, in_spike, out_spike, trace_pre, trace_post, tau_pre, tau_post, f_pre=<function <lambda>>, f_post=<function <lambda>>)[源代码]#

API Language - 中文 | English

  • 中文

对单步脉冲输入执行二维卷积层的 STDP 更新。

当前仅支持 dilation == (1, 1) 且 groups == 1 的卷积。

参数:

  • conv (Conv2d) -- 需要执行 STDP 的二维卷积层

  • in_spike (Tensor) -- 输入脉冲，shape = [batch_size, C_in, H_in, W_in]

  • out_spike (Tensor) -- 输出脉冲，shape = [batch_size, C_out, H_out, W_out]

  • trace_pre (Union[Tensor, None]) -- pre-synaptic trace。若为 None，则初始化为与 in_spike 同形状零张量

  • trace_post (Union[Tensor, None]) -- post-synaptic trace。若为 None，则初始化为与 out_spike 同形状零张量

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

返回:

(trace_pre, trace_post, delta_w)，其中 delta_w 的形状与 conv.weight 相同

返回类型:

tuple[Tensor, Tensor, Tensor]

抛出:

NotImplementedError -- 当 conv.dilation != (1, 1) 或 conv.groups != 1 时抛出

  • English

Apply one STDP update step to a 2D convolution layer driven by single-step spike inputs.

Only convolutions with dilation == (1, 1) and groups == 1 are currently supported.

参数:

  • conv (Conv2d) -- 2D convolution layer updated by STDP

  • in_spike (Tensor) -- Input spikes with shape = [batch_size, C_in, H_in, W_in]

  • out_spike (Tensor) -- Output spikes with shape = [batch_size, C_out, H_out, W_out]

  • trace_pre (Union[Tensor, None]) -- Pre-synaptic trace. If None, initialized as zeros with the same shape as in_spike

  • trace_post (Union[Tensor, None]) -- Post-synaptic trace. If None, initialized as zeros with the same shape as out_spike

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

返回:

(trace_pre, trace_post, delta_w), where delta_w has the same shape as conv.weight

返回类型:

tuple[Tensor, Tensor, Tensor]

抛出:

NotImplementedError -- Raised when conv.dilation != (1, 1) or conv.groups != 1

spikingjelly.activation_based.learning.stdp_conv1d_single_step(conv, in_spike, out_spike, trace_pre, trace_post, tau_pre, tau_post, f_pre=<function <lambda>>, f_post=<function <lambda>>)[源代码]#

API Language - 中文 | English

  • 中文

对单步脉冲输入执行一维卷积层的 STDP 更新。

当前仅支持 dilation == (1,) 且 groups == 1 的卷积。

参数:

  • conv (Conv1d) -- 需要执行 STDP 的一维卷积层

  • in_spike (Tensor) -- 输入脉冲，shape = [batch_size, C_in, L_in]

  • out_spike (Tensor) -- 输出脉冲，shape = [batch_size, C_out, L_out]

  • trace_pre (Union[Tensor, None]) -- pre-synaptic trace。若为 None，则初始化为与 in_spike 同形状零张量

  • trace_post (Union[Tensor, None]) -- post-synaptic trace。若为 None，则初始化为与 out_spike 同形状零张量

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

返回:

(trace_pre, trace_post, delta_w)，其中 delta_w 的形状与 conv.weight 相同

返回类型:

tuple[Tensor, Tensor, Tensor]

抛出:

NotImplementedError -- 当 conv.dilation != (1,) 或 conv.groups != 1 时抛出

  • English

Apply one STDP update step to a 1D convolution layer driven by single-step spike inputs.

Only convolutions with dilation == (1,) and groups == 1 are currently supported.

参数:

  • conv (Conv1d) -- 1D convolution layer updated by STDP

  • in_spike (Tensor) -- Input spikes with shape = [batch_size, C_in, L_in]

  • out_spike (Tensor) -- Output spikes with shape = [batch_size, C_out, L_out]

  • trace_pre (Union[Tensor, None]) -- Pre-synaptic trace. If None, initialized as zeros with the same shape as in_spike

  • trace_post (Union[Tensor, None]) -- Post-synaptic trace. If None, initialized as zeros with the same shape as out_spike

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

返回:

(trace_pre, trace_post, delta_w), where delta_w has the same shape as conv.weight

返回类型:

tuple[Tensor, Tensor, Tensor]

抛出:

NotImplementedError -- Raised when conv.dilation != (1,) or conv.groups != 1

spikingjelly.activation_based.learning.stdp_multi_step(layer, in_spike, out_spike, trace_pre, trace_post, tau_pre, tau_post, f_pre=<function <lambda>>, f_post=<function <lambda>>)[源代码]#

API Language - 中文 | English

  • 中文

对线性层、一维卷积层或二维卷积层执行多步 STDP 更新。

该函数沿时间维遍历 in_spike 与 out_spike，并在每个时间步调用对应的 单步 STDP 规则，最终累加得到整段序列的权重增量。

参数:

  • layer (Union[Linear, Conv1d, Conv2d]) -- 支持的突触层，目前为 nn.Linear、nn.Conv1d 或 nn.Conv2d

  • in_spike (Tensor) -- 输入脉冲序列，时间维位于第 0 维

  • out_spike (Tensor) -- 输出脉冲序列，时间维位于第 0 维

  • trace_pre (Union[float, Tensor, None]) -- pre-synaptic trace 的初始值

  • trace_post (Union[float, Tensor, None]) -- post-synaptic trace 的初始值

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

返回:

(trace_pre, trace_post, delta_w)，其中 delta_w 的形状与 layer.weight 相同

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

  • English

Apply multi-step STDP updates to a linear layer, a 1D convolution layer, or a 2D convolution layer.

The function iterates over the time dimension of in_spike and out_spike, applies the matching single-step STDP rule at each time step, and accumulates the weight increment over the whole sequence.

参数:

  • layer (Union[Linear, Conv1d, Conv2d]) -- Supported synaptic layer. Currently nn.Linear, nn.Conv1d or nn.Conv2d

  • in_spike (Tensor) -- Input spike sequence with the time axis at dimension 0

  • out_spike (Tensor) -- Output spike sequence with the time axis at dimension 0

  • trace_pre (Union[float, Tensor, None]) -- Initial value of the pre-synaptic trace

  • trace_post (Union[float, Tensor, None]) -- Initial value of the post-synaptic trace

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

返回:

(trace_pre, trace_post, delta_w), where delta_w has the same shape as layer.weight

返回类型:

tuple[Union[float, Tensor], Union[float, Tensor], Tensor]

class spikingjelly.activation_based.learning.STDPLearner(step_mode, synapse, sn, tau_pre, tau_post, f_pre=<function STDPLearner.<lambda>>, f_post=<function STDPLearner.<lambda>>)[源代码]#

基类：MemoryModule

API Language - 中文 | English

  • 中文

基于监视器的 STDP 学习器。

该学习器通过 InputMonitor 和 OutputMonitor 自动记录突触层输入脉冲与神经元输出脉冲，并在调用 step() 时根据 step_mode 选择单步或多步 STDP 规则。

参数:

  • step_mode (str) -- 's' 表示单步 STDP，'m' 表示多步 STDP

  • synapse (Union[Conv2d, Linear]) -- 需要执行 STDP 的突触层，目前支持 nn.Linear、nn.Conv1d、nn.Conv2d

  • sn (spikingjelly.activation_based.neuron.BaseNode) -- 产生输出脉冲的脉冲神经元模块

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

  • English

Monitor-based STDP learner.

The learner automatically records synaptic input spikes and neuronal output spikes with InputMonitor and OutputMonitor. When step() is called, it selects the single-step or multi-step STDP rule according to step_mode.

参数:

  • step_mode (str) -- 's' for single-step STDP and 'm' for multi-step STDP

  • synapse (Union[Conv2d, Linear]) -- Synaptic layer updated by STDP. Currently supports nn.Linear, nn.Conv1d, and nn.Conv2d

  • sn (spikingjelly.activation_based.neuron.BaseNode) -- Spiking neuron module that generates output spikes

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

reset()[源代码]#

API Language - 中文 | English

  • 中文

重置学习器内部状态，并清空输入/输出脉冲监视器中已记录的数据。

  • English

Reset the learner state and clear all recorded data in the input/output spike monitors.

disable()[源代码]#

API Language - 中文 | English

  • 中文

禁用输入脉冲与输出脉冲监视器，使其停止记录新数据。

  • English

Disable the input and output spike monitors so they stop recording new data.

enable()[源代码]#

API Language - 中文 | English

  • 中文

启用输入脉冲与输出脉冲监视器，使其恢复记录。

  • English

Enable the input and output spike monitors so they resume recording.

step(on_grad=True, scale=1.0)[源代码]#

API Language - 中文 | English

  • 中文

使用当前监视器中缓存的脉冲记录执行一次 STDP 权重更新。

当 on_grad=True 时，函数会把 -delta_w 累加到 self.synapse.weight.grad； 当 on_grad=False 时，返回累计的 delta_w 而不写入梯度。

参数:

  • on_grad (bool) -- 是否将权重增量写入 self.synapse.weight.grad

  • scale (float) -- 对累计权重增量施加的缩放因子

返回:

当 on_grad=False 时返回累计的权重增量；否则返回 None

返回类型:

Optional[Tensor]

抛出:

  • NotImplementedError -- 当 self.step_mode 与突触层类型组合当前不受支持时抛出

  • ValueError -- 当 self.step_mode 不是 's' 或 'm' 时抛出

  • English

Perform one STDP update using the spike records currently buffered in the monitors.

When on_grad=True, the function accumulates -delta_w into self.synapse.weight.grad. When on_grad=False, it returns the accumulated delta_w without writing gradients.

参数:

  • on_grad (bool) -- Whether to write the weight increment into self.synapse.weight.grad

  • scale (float) -- Scaling factor applied to the accumulated weight increment

返回:

The accumulated weight increment when on_grad=False; otherwise None

返回类型:

Optional[Tensor]

抛出:

  • NotImplementedError -- Raised when the current step_mode / synapse-type combination is unsupported

  • ValueError -- Raised when self.step_mode is neither 's' nor 'm'

class spikingjelly.activation_based.learning.MSTDPLearner(step_mode, batch_size, synapse, sn, tau_pre, tau_post, f_pre=<function MSTDPLearner.<lambda>>, f_post=<function MSTDPLearner.<lambda>>)[源代码]#

基类：MemoryModule

API Language - 中文 | English

  • 中文

reward-modulated STDP（mSTDP）学习器。

该学习器维护每个样本对应的 eligibility，并在 step() 中结合外部奖励 reward 把 eligibility 转换为权重更新。

参数:

  • step_mode (str) -- 's' 表示单步 mSTDP

  • batch_size (float) -- 每次奖励调制时使用的 batch 大小

  • synapse (Union[Conv2d, Linear]) -- 需要执行 mSTDP 的突触层

  • sn (spikingjelly.activation_based.neuron.BaseNode) -- 产生输出脉冲的脉冲神经元模块

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

  • English

Reward-modulated STDP (mSTDP) learner.

The learner maintains per-sample eligibility tensors and converts them into weight updates inside step() using the external reward reward.

参数:

  • step_mode (str) -- 's' for single-step mSTDP

  • batch_size (float) -- Batch size used when modulating eligibility with rewards

  • synapse (Union[Conv2d, Linear]) -- Synaptic layer updated by mSTDP

  • sn (spikingjelly.activation_based.neuron.BaseNode) -- Spiking neuron module that generates output spikes

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

reset()[源代码]#

API Language - 中文 | English

  • 中文

重置学习器内部状态，并清空监视器缓存。

  • English

Reset the learner state and clear the monitor buffers.

disable()[源代码]#

API Language - 中文 | English

  • 中文

禁用输入/输出监视器。

  • English

Disable the input/output monitors.

enable()[源代码]#

API Language - 中文 | English

  • 中文

启用输入/输出监视器。

  • English

Enable the input/output monitors.

step(reward, on_grad=True, scale=1.0)[源代码]#

API Language - 中文 | English

  • 中文

使用外部奖励 reward 对当前 eligibility 进行调制，并生成一次 mSTDP 权重更新。 若 reward 为张量，则在计算前将其从 autograd 计算图中分离， 因此写入的 weight.grad 或返回的权重增量不会连接到 reward 的计算图。

参数:

  • reward (Tensor) -- 每个样本对应的奖励，通常 shape = [batch_size]。 张量奖励会在计算前分离

  • on_grad (bool) -- 是否将结果写入 self.synapse.weight.grad

  • scale (float) -- 权重增量的缩放因子

返回:

当 on_grad=False 时返回累计的权重增量；否则返回 None

返回类型:

Optional[Tensor]

抛出:

  • English

Modulate the current eligibility with the external reward reward and generate one mSTDP weight update. Tensor rewards are detached from the autograd graph before computation, so neither the written weight.grad nor the returned weight increment is connected to the reward graph.

参数:

  • reward (Tensor) -- Reward for each sample, typically with shape = [batch_size]. Tensor rewards are detached before computation

  • on_grad (bool) -- Whether to write the result into self.synapse.weight.grad

  • scale (float) -- Scaling factor applied to the weight increment

返回:

The accumulated weight increment when on_grad=False; otherwise None

返回类型:

Optional[Tensor]

抛出:

  • NotImplementedError -- Only some step_mode / synapse-type combinations are currently supported

  • ValueError -- Raised when self.step_mode is invalid

class spikingjelly.activation_based.learning.MSTDPETLearner(step_mode, synapse, sn, tau_pre, tau_post, tau_trace, f_pre=<function MSTDPETLearner.<lambda>>, f_post=<function MSTDPETLearner.<lambda>>)[源代码]#

基类：MemoryModule

API Language - 中文 | English

  • 中文

mSTDP-ET 学习器。

与 MSTDPLearner 相比，该学习器额外维护随时间衰减的 eligibility trace trace_e，并在 step() 中结合奖励生成最终权重更新。

参数:

  • step_mode (str) -- 's' 表示单步 mSTDP-ET

  • synapse (Union[Conv2d, Linear]) -- 需要执行 mSTDP-ET 的突触层

  • sn (spikingjelly.activation_based.neuron.BaseNode) -- 产生输出脉冲的脉冲神经元模块

  • tau_pre (float) -- pre trace 的时间常数

  • tau_post (float) -- post trace 的时间常数

  • tau_trace (float) -- eligibility trace 的时间常数

  • f_pre (Callable) -- pre 分支的权重调制函数

  • f_post (Callable) -- post 分支的权重调制函数

  • English

mSTDP-ET learner.

Compared with MSTDPLearner, this learner additionally maintains a temporally decaying eligibility trace trace_e and combines it with rewards inside step() to produce the final weight update.

参数:

  • step_mode (str) -- 's' for single-step mSTDP-ET

  • synapse (Union[Conv2d, Linear]) -- Synaptic layer updated by mSTDP-ET

  • sn (spikingjelly.activation_based.neuron.BaseNode) -- Spiking neuron module that generates output spikes

  • tau_pre (float) -- Time constant of the pre trace

  • tau_post (float) -- Time constant of the post trace

  • tau_trace (float) -- Time constant of the eligibility trace

  • f_pre (Callable) -- Weight modulation function for the pre branch

  • f_post (Callable) -- Weight modulation function for the post branch

reset()[源代码]#

API Language - 中文 | English

  • 中文

重置学习器内部状态，并清空监视器缓存。

  • English

Reset the learner state and clear the monitor buffers.

disable()[源代码]#

API Language - 中文 | English

  • 中文

禁用输入/输出监视器。

  • English

Disable the input/output monitors.

enable()[源代码]#

API Language - 中文 | English

  • 中文

启用输入/输出监视器。

  • English

Enable the input/output monitors.

step(reward, on_grad=True, scale=1.0)[源代码]#

API Language - 中文 | English

  • 中文

使用外部奖励 reward 对 eligibility trace 进行调制，并生成一次 mSTDP-ET 权重更新。 若 reward 为张量，则在计算前将其从 autograd 计算图中分离， 因此写入的 weight.grad 或返回的权重增量不会连接到 reward 的计算图。

参数:

  • reward (Tensor) -- 奖励信号，通常为标量或 shape = [batch_size] 的张量。 张量奖励会在计算前分离

  • on_grad (bool) -- 是否将结果写入 self.synapse.weight.grad

  • scale (float) -- 权重增量的缩放因子

返回:

当 on_grad=False 时返回累计的权重增量；否则返回 None

返回类型:

Optional[Tensor]

抛出:

  • English

Modulate the eligibility trace with the external reward reward and generate one mSTDP-ET weight update. Tensor rewards are detached from the autograd graph before computation, so neither the written weight.grad nor the returned weight increment is connected to the reward graph.

参数:

  • reward (Tensor) -- Reward signal, typically a scalar or a tensor with shape = [batch_size]. Tensor rewards are detached before computation

  • on_grad (bool) -- Whether to write the result into self.synapse.weight.grad

  • scale (float) -- Scaling factor applied to the weight increment

返回:

The accumulated weight increment when on_grad=False; otherwise None

返回类型:

Optional[Tensor]

抛出:

  • NotImplementedError -- Only some step_mode / synapse-type combinations are currently supported

  • ValueError -- Raised when self.step_mode is invalid