spark.nn.interfaces.output.exponential

spark.nn.interfaces.output.exponential#

Classes#

`ExponentialIntegratorConfig`	ExponentialIntegrator configuration class.
`ExponentialIntegrator`	Transforms a discrete spike signal to a continuous signal.

Module Contents#

class spark.nn.interfaces.output.exponential.ExponentialIntegratorConfig(__skip_validation__=False, **kwargs)[source]#

Bases: spark.nn.interfaces.output.base.OutputInterfaceConfig

ExponentialIntegrator configuration class.

Parameters:: __skip_validation__ (bool)

num_outputs: int[source]#

saturation_freq: float[source]#

tau: float[source]#

output_map: jax.Array | None[source]#

shuffle: bool[source]#

smooth_trace: bool[source]#

class spark.nn.interfaces.output.exponential.ExponentialIntegrator(config=None, **kwargs)[source]#

Bases: spark.nn.interfaces.output.base.OutputInterface

Transforms a discrete spike signal to a continuous signal. This transformation assumes a very simple integration model model without any type of adaptation or plasticity. Spikes are grouped into k non-overlaping clusters and every neuron contributes the same amount to the ouput.

Init:: num_outputs: int saturation_freq: float [Hz] tau: float [ms] shuffle: bool smooth_trace: bool
Input:: spikes: SpikeArray
Output:: signal: FloatArray