PySpikingHandlerModel

Full Name

neuroptimiser.core.models.PySpikingHandlerModel

Description

class PySpikingHandlerModel

Bases: PyLoihiProcessModel

Spiking handler model for Loihi-based perturbation-based nheuristics

This model handles the spiking signals in a nheuristic process, allowing the spiking core read and write spikes to the input and output ports to the external world.

See also

neuroptimiser.core.processes.SpikingHandler

Process that handles spiking signals in a NeuroHeuristicUnit.

__init__(proc_params)

Initialises the spiking handler model with the given parameters.

Arguments

proc_paramsdict

Dictionary containing the parameters for the process model. It must include:

• agent_id: int, identifier of the agent

• internal_shape: tuple, shape of the internal state (e.g., number of dimensions)

• external_shape: tuple, shape of the external state (e.g., number of agents and dimensions)

a_in: PyInPort = LavaPyType(cls=<class 'lava.magma.core.model.py.ports.PyInPortVectorDense'>, d_type=<class 'bool'>, precision=None)

a_out: PyOutPort = LavaPyType(cls=<class 'lava.magma.core.model.py.ports.PyOutPortVectorDense'>, d_type=<class 'bool'>, precision=None)

implements_process

alias of SpikingHandler

implements_protocol

alias of LoihiProtocol

required_resources: ty.List[ty.Type[AbstractResource]] = [<class 'lava.magma.core.resources.CPU'>]

run_spk()

Runs the spiking handler process model.

The process is summarised as follows:

1. Receives the input spikes and activation matrix from the inports.

2. Prepares the output spikes based on the input spikes and sends them to the outports.

s_in: PyInPort = LavaPyType(cls=<class 'lava.magma.core.model.py.ports.PyInPortVectorDense'>, d_type=<class 'bool'>, precision=None)

s_out: PyOutPort = LavaPyType(cls=<class 'lava.magma.core.model.py.ports.PyOutPortVectorDense'>, d_type=<class 'bool'>, precision=None)