hxtorch.spiking.modules.SparseSynapse

class hxtorch.spiking.modules.SparseSynapse(connections: torch.SparseTensor, experiment: Experiment, chip_coordinate: Optional[Tuple[grenade.common.ChipOnConnection, grenade.common.ConnectionOnExecutor]] = None, device: str = None, dtype: Type = None, transform: Callable = <function linear_saturating>)

Bases: hxtorch.spiking.modules.types.projection.Projection

Sparse synapse layer

Caveat: For execution on hardware, this module can only be used in conjuction with a subsequent Neuron module.

__init__(connections: torch.SparseTensor, experiment: Experiment, chip_coordinate: Optional[Tuple[grenade.common.ChipOnConnection, grenade.common.ConnectionOnExecutor]] = None, device: str = None, dtype: Type = None, transform: Callable = <function linear_saturating>) → None

A sparse projection, with connections defined by non-zero entries in connections, represented sparsely on hardware.

Parameters

  • connections – A tensor of shape (in_features, out_features) defining existing connections by one-entries. Can be sparse or non-sparse.

  • experiment – Experiment to append layer to.

  • chip_coordinate – Chip coordinate this module is placed on.

  • device – Device to execute on. Only considered in mock-mode.

  • dtype – Data type of weight tensor.

  • transform – A function taking the modules weight tensor and transforms it into weights mappable to hardware.

Methods

__init__(connections, experiment[, …])

A sparse projection, with connections defined by non-zero entries in connections, represented sparsely on hardware.

extra_repr()

Add additional information

forward_func(input)

get_connections()

reset_parameters()

Resets the synapses weights by reinitialization using torch.nn.kaiming_uniform_.

Attributes

changed_input_data: bool
changed_topology: bool
connections: torch.Tensor
extra_repr() → str

Add additional information

forward_func(input: types.Handle_current_membrane_cadc_membrane_madc_spikes) → types.Handle_graded_spikes
get_connections() → List[grenade.network.Connection]
in_features: int
out_features: int
output_type

alias of types.Handle_graded_spikes

reset_parameters() → None

Resets the synapses weights by reinitialization using torch.nn.kaiming_uniform_.

training: bool
weight: torch.Tensor