jaxsnn.event.modules.hx

Modules

jaxsnn.event.modules.hx.input

jaxsnn.event.modules.hx.lif

jaxsnn.event.modules.hx.linear

Classes

NeuronParameters(tau_syn, tau_mem, v_th, …)

Functions

jaxsnn.event.modules.hx.HXLIF(size: int, n_steps: int, params: NeuronParameters, time_offset: float = 0.0, n_hw_spikes: Optional[int] = None, chip_coordinate: Optional[DLSGlobal] = None, enable_spike_recording: bool = True, enable_cadc_recording: bool = False, enable_cadc_recording_placement_in_dram: bool = False, enable_madc_recording: bool = False, record_neuron_id: Optional[int] = None, placement_constraint: Optional[List[halco.LogicalNeuronOnDLS]] = None, neuron_structure: Optional[Morphology] = None, **extra_params) → Population

Create a LIF neuron population for execution on BrainScaleS.

Parameters

  • size – Number of neurons in the population.

  • n_steps – Number of simulation steps.

  • params – Neuron parameters (hardware-compatible).

  • time_offset – Optional time offset for all neurons.

  • n_hw_spikes – Optional hardware spike limit.

  • chip_coordinate – Optional chip coordinate for placement.

  • enable_spike_recording – Enable spike recording.

  • enable_cadc_recording – Enable CADC recording.

  • enable_cadc_recording_placement_in_dram – Place CADC recording in DRAM.

  • enable_madc_recording – Enable MADC recording.

  • record_neuron_id – Restrict recording to a specific neuron.

  • placement_constraint – Placement constraints for neurons.

  • neuron_structure – Optional neuron morphology.

  • extra_params – Additional hardware-specific parameters.

Returns

Population object for hardware LIF neurons.

jaxsnn.event.modules.hx.HXLinear(mean: float = 0.5, std: float = 2.0, min_delay: float = 0.0, weight_scale: float = 1.0, chip_coordinate: Optional[pyhalco_hicann_dls_vx_v3.DLSGlobal, None] = None, transform: Callable = <function linear_saturating>) → jaxsnn.event.types.Projection

Creates a synapse initialization function and associated parameters.

Parameters

  • mean – Mean value for initializing synaptic weights.

  • std – Standard deviation for initializing synaptic weights.

  • min_delay – Minimum allowable synaptic delay.

  • weight_scale – Scaling factor for synaptic weights.

  • chip_coordinate – Chip coordinate for hardware execution.

  • transform – Transformation function applied to synaptic weights.

Returns

Projection instance containing generator function and parameters.

jaxsnn.event.modules.hx.HXSource(size: int, n_events: int, chip_coordinate: Optional[pyhalco_hicann_dls_vx_v3.DLSGlobal, None] = None, enable_spike_loopback: bool = False) → jaxsnn.event.types.SourcePopulation

Create an input layer descriptor.

The init_fn, state_fn, and event_fn returned by the generator return None because they are not needed.

Parameters

  • size – Number of neurons in the input layer.

  • n_events – Number of events to generate.

  • chip_coordinate – Chip coordinate for hardware execution.

  • enable_spike_loopback – Whether to enable spike loopback.

Returns

SourcePopulation instance.