hxtorch.spiking.modules.types.Population

class hxtorch.spiking.modules.types.Population(size: int, experiment: Experiment, execution_instance: Optional[ExecutionInstance] = None, chip_coordinate: Optional[DLSGlobal] = None, **hxparams: Dict[str, ModuleParameterType])

Bases: hxtorch.spiking.modules.types.BasePopulation

Base class for on-chip populations on BSS-2

__init__(size: int, experiment: Experiment, execution_instance: Optional[ExecutionInstance] = None, chip_coordinate: Optional[DLSGlobal] = None, **hxparams: Dict[str, ModuleParameterType]) → None

Parameters

• size – Number of input neurons.

• experiment – Experiment to append layer to.

• execution_instance – Execution instance to place to.

• chip_coordinate – Chip coordinate this module is placed on.

Methods

__init__(size, experiment[, …])	param size Number of input neurons.
calib_changed_since_last_run()
calibration_from_params(targets, neurons)	Add population specific calibration targets to the experiment-wide calibration target, which holds information for all populations.
extra_repr()	Add additional information
has_trainable_params()	Check whether population has trainable parameters.
params_dict()
params_from_calibration(targets, neurons)
set_trainable_params(chip)

Attributes

calib_changed_since_last_run() → bool

calibration_from_params(targets: SpikingCalibTarget, neurons) → SpikingCalibTarget

Add population specific calibration targets to the experiment-wide calibration target, which holds information for all populations.

Parameters

spiking_calib_target – Calibration target parameters of all neuron populations registered in the self.experiment instance.

Returns

The chip_wide_calib_target with adjusted parameters.

extra_repr() → str

Add additional information

has_trainable_params() → bool

Check whether population has trainable parameters.

params_dict() → Dict

params_from_calibration(targets: SpikingCalibTarget, neurons) → None

set_trainable_params(chip)

size: int

training: bool