tether package

Subpackages

• tether.data package
  • Submodules
  • tether.data.encoding module
    • SpikingDatasetWrapper
    • latency_encoding()
    • rate_encoding()
  • Module contents
    • SpikingDatasetWrapper
    • latency_encoding()
    • rate_encoding()
• tether.functional package
  • Submodules
  • tether.functional.alif module
    • ALIFSubFunction
      • ALIFSubFunction.backward()
      • ALIFSubFunction.forward()
  • tether.functional.lif module
    • LIFSubFunction
      • LIFSubFunction.backward()
      • LIFSubFunction.forward()
  • tether.functional.plif module
    • PLIFSubFunction
      • PLIFSubFunction.backward()
      • PLIFSubFunction.forward()
  • Module contents
• tether.kernels package
  • Submodules
  • tether.kernels.alif module
  • tether.kernels.lif module
  • tether.kernels.plif module
  • Module contents
• tether.nn package
  • Submodules
  • tether.nn.alif module
    • ALIF
      • ALIF.forward()
  • tether.nn.attention module
    • SpikingSelfAttention
      • SpikingSelfAttention.forward()
      • SpikingSelfAttention.reset_states()
  • tether.nn.block module
    • SpikingTransformerBlock
      • SpikingTransformerBlock.forward()
  • tether.nn.lif module
    • LIF
      • LIF.alpha
      • LIF.forward()
  • tether.nn.plif module
    • PLIF
      • PLIF.forward()
  • tether.nn.surrogates module
    • Arctan
      • Arctan.get_id()
    • FastSigmoid
      • FastSigmoid.get_id()
    • Sigmoid
      • Sigmoid.get_id()
    • Surrogate
      • Surrogate.get_id()
  • Module contents
    • ALIF
      • ALIF.forward()
    • Arctan
      • Arctan.get_id()
    • FastSigmoid
      • FastSigmoid.get_id()
    • LIF
      • LIF.alpha
      • LIF.forward()
    • PLIF
      • PLIF.forward()
    • Sigmoid
      • Sigmoid.get_id()
    • SpikingSelfAttention
      • SpikingSelfAttention.forward()
      • SpikingSelfAttention.reset_states()
    • SpikingTransformerBlock
      • SpikingTransformerBlock.forward()
    • Surrogate
      • Surrogate.get_id()

Module contents

class tether.ALIF(n_neurons, decay_v=0.9, decay_a=0.9, threshold=1.0, beta=0.5, alpha=2.0, store_traces=False)

Bases: Module

forward(x_seq)

Forward pass of the ALIF module.

Parameters:

x_seq (torch.Tensor) – Input sequence.

Returns:

Output spikes with the same shape as input.

Return type:

torch.Tensor

class tether.Arctan(alpha=2.0, trainable=False)

Bases: Surrogate

Arctan surrogate gradient.

The surrogate derivative is given by:

\[\begin{split}f'(x) = \\frac{1}{1 + (\\alpha \\pi x)^2}\end{split}\]

where x is the normalized membrane potential (v - threshold).

get_id()

Return the integer ID corresponding to the surrogate type used in Triton kernels.

Returns:

Surrogate type ID.

Return type:

int

class tether.FastSigmoid(alpha=2.0, trainable=False)

Bases: Surrogate

Fast Sigmoid (approximated) surrogate gradient.

Uses a computationally cheaper approximation of the sigmoid derivative:

\[\begin{split}f'(x) = \\frac{1}{(1 + |\\alpha x|)^2}\end{split}\]

This avoids expensive exponential operations.

get_id()

Return the integer ID corresponding to the surrogate type used in Triton kernels.

Returns:

Surrogate type ID.

Return type:

int

class tether.LIF(n_neurons, decay=0.9, threshold=1.0, alpha=2.0, surrogate=None, store_traces=False)

Bases: Module

property alpha

forward(x_seq)

Forward pass of the LIF module.

Parameters:

x_seq (torch.Tensor) – Input sequence.

Returns:

Output spikes with the same shape as input.

Return type:

torch.Tensor

class tether.PLIF(n_neurons, init_decay=0.9, init_threshold=1.0, alpha=2.0, surrogate=None, store_traces=False)

Bases: Module

forward(x_seq)

Forward pass of the PLIF module.

Parameters:

x_seq (torch.Tensor) – Input sequence of shape (Time, Batch, Neurons) or (Time, Batch * Neurons).

Returns:

Output spikes with the same shape as input.

Return type:

torch.Tensor

class tether.Sigmoid(alpha=2.0, trainable=False)

Bases: Surrogate

Sigmoid surrogate gradient.

The surrogate function is a sigmoid, and its derivative is:

\[\begin{split}f'(x) = \\alpha \\cdot \\sigma(\\alpha x) \\cdot (1 - \\sigma(\\alpha x))\end{split}\]

where \(\\sigma\) is the logistic sigmoid function and x is the membrane potential gap.

get_id()

Return the integer ID corresponding to the surrogate type used in Triton kernels.

Returns:

Surrogate type ID.

Return type:

int

class tether.SpikingSelfAttention(dim, num_heads=8, decay=0.9, threshold=1.0)

Bases: Module

forward(x_seq)

Forward pass of the SpikingSelfAttention.

Parameters:

x_seq (torch.Tensor) – Input sequence of shape (T, B, N, D).

Returns:

Output sequence of shape (T, B, N, D).

Return type:

torch.Tensor

reset_states()

Reset the KV state buffer to zeros.

class tether.SpikingTransformerBlock(dim, num_heads=8, mlp_ratio=4)

Bases: Module

forward(x)

Forward pass of the SpikingTransformerBlock.

Parameters:

x (torch.Tensor) – Input tensor.

Returns:

Output tensor.

Return type:

torch.Tensor

class tether.Surrogate(alpha=2.0, trainable=False)

Bases: Module

Base class for surrogate gradient functions used in Spiking Neural Networks.

Surrogate gradients allow for backpropagation through the non-differentiable Heaviside step function used for spike generation.

Parameters:

• alpha (float, optional) – Scaling parameter that controls the steepness/width of the surrogate derivative. Default is 2.0.

• trainable (bool, optional) – If True, alpha becomes a learnable parameter. Default is False.

get_id()

Return the integer ID corresponding to the surrogate type used in Triton kernels.

Returns:

Surrogate type ID.

Return type:

int