hxtorch.spiking.functional.eventprop
Classes
|
Define gradient using adjoint code (EventProp) from norse |
|
Synapse function for proper gradient transport when using EventPropNeuron. |
|
Typed version of namedtuple. |
Functions
-
hxtorch.spiking.functional.eventprop.
eventprop_neuron
(input: torch.Tensor, params: NamedTuple, dt: float, hw_data: Optional[torch.Tensor]) → Tuple[torch.Tensor]
-
hxtorch.spiking.functional.eventprop.
eventprop_synapse
(input: torch.Tensor, weight: torch.Tensor, _: Optional[torch.Tensor] = None) → torch.Tensor