API reference

Branch-ELM compatibility

Signatures, parameters, return contracts, and source for branch-elm compatibility.

Overview

BranchELM and BranchELMConfig provide the baseline and checkpoint-compatible branched neuron implementation. Inputs use (batch, time, input_channels); the standard two-channel readout contains a spike logit and a soma target coordinate.

Source revision: caef7be03abd. Public export index.

BranchELMConfig

axosim.model.BranchELMConfig(input_dim: int = 1278, memory_units: int = 30, num_branches: int = 32, hidden_units: int = 64, synapse_decay: float = 0.85, memory_decay: float = 0.9)

Source

Dimensions and decay constants for the branched recurrent neuron.

Parameters

input_dim int
default=1278. Native input-channel count.
memory_units int
default=30. Width of the recurrent memory state.
num_branches int
default=32. Number of branched input features.
hidden_units int
default=64. Width of the hidden feature layer.
synapse_decay float
default=0.85. Decay coefficient of the synaptic trace.
memory_decay float
default=0.9. Decay coefficient of recurrent memory.

Attributes

Constructor fields are retained as read-only attributes.

Methods

BranchELMConfig.branch_elm_30

@classmethod
axosim.model.BranchELMConfig.branch_elm_30(*, input_dim: int=1278, num_branches: int=32) -> 'BranchELMConfig'

Source

Parameters

input_dim int
keyword-only, default=1278. Native input-channel count.
num_branches int
keyword-only, default=32. Number of branched input features.

Returns

'BranchELMConfig'

BranchELM

axosim.model.BranchELM(config: BranchELMConfig)

Source

Branch-factorized recurrent surrogate with spike and soma outputs.

Bases: nn.Module.

Parameters

config BranchELMConfig
required. Model configuration; use the defaults and constraints documented for its configuration class.

Methods

BranchELM.forward

axosim.model.BranchELM.forward(x: torch.Tensor) -> torch.Tensor

Source

Predict native spike and soma outputs for the supplied sequence.

x must be (B,T,config.input_dim). Returns (B,T,2), with one spike logit and one soma target coordinate per step. Synaptic and memory states start at zero for each call.

Parameters

x torch.Tensor
required. Input tensor for the full-sequence or streaming operation.

Returns

prediction torch.Tensor
Spike-logit and soma-target channels in the tensor shape specified above.

BranchELM.parameter_count

axosim.model.BranchELM.parameter_count() -> int

Source

Return the count of trainable parameters.

Returns

int

Search guides, examples, and API signatures.