spark.nn.neurons

Contents

spark.nn.neurons#

Submodules#

Classes#

`Neuron`	Abstract Neuron model.
`NeuronConfig`	Abstract Neuron model configuration class.
`NeuronOutput`	Generic Neuron model output spec.
`LIFNeuron`	Leaky Integrate and Fire neuronal model.
`LIFNeuronConfig`	LIFNeuron configuration class.
`ALIFNeuron`	Leaky integrate and fire neuronal model.
`ALIFNeuronConfig`	ALIFNeuron configuration class.

Package Contents#

class spark.nn.neurons.Neuron(config=None, **kwargs)[source]#

Bases: spark.core.module.SparkModule, abc.ABC, Generic[ConfigT]

Abstract Neuron model.

This is a convenience class used to synchronize data more easily. Can be thought as the equivalent of Sequential in standard ML frameworks.

Parameters:: config (ConfigT | None)

config: ConfigT[source]#

units[source]#

reset()[source]#: Resets neuron states to their initial values.

abstractmethod __call__(in_spikes)[source]#

Execution method.

Parameters:: in_spikes (spark.core.payloads.SpikeArray)
Return type:: NeuronOutput

class spark.nn.neurons.NeuronConfig(**kwargs)[source]#

Bases: spark.core.config.SparkConfig

Abstract Neuron model configuration class.

units: tuple[int, Ellipsis][source]#

class spark.nn.neurons.NeuronOutput[source]#

Bases: TypedDict

Generic Neuron model output spec.

Initialize self. See help(type(self)) for accurate signature.

out_spikes: spark.core.payloads.SpikeArray[source]#

class spark.nn.neurons.LIFNeuron(config=None, **kwargs)[source]#

Bases: spark.nn.neurons.Neuron

Leaky Integrate and Fire neuronal model.

Parameters:: config (LIFNeuronConfig | None)

config: LIFNeuronConfig[source]#

soma: spark.nn.components.somas.leaky.LeakySoma[source]#

delays: spark.nn.components.delays.base.Delays[source]#

synapses: spark.nn.components.synapses.base.Synanpses[source]#

learning_rule: spark.nn.components.learning_rules.base.LearningRule[source]#

max_delay[source]#

inhibitory_rate[source]#

async_spikes[source]#

build(input_specs)[source]#

Build method.

Parameters:: input_specs (dict[str, spark.core.specs.InputSpec])

__call__(in_spikes)[source]#

Update neuron’s states and compute spikes.

Parameters:: in_spikes (spark.core.payloads.SpikeArray)
Return type:: spark.nn.neurons.NeuronOutput

class spark.nn.neurons.LIFNeuronConfig(**kwargs)[source]#

Bases: spark.nn.neurons.NeuronConfig

LIFNeuron configuration class.

max_delay: float[source]#

inhibitory_rate: float[source]#

async_spikes: bool[source]#

soma_config: spark.nn.components.somas.leaky.LeakySomaConfig[source]#

synapses_config: spark.nn.components.synapses.base.SynanpsesConfig[source]#

delays_config: spark.nn.components.delays.base.DelaysConfig[source]#

learning_rule_config: spark.nn.components.learning_rules.base.LearningRuleConfig[source]#

class spark.nn.neurons.ALIFNeuron(config=None, **kwargs)[source]#

Bases: spark.nn.neurons.Neuron

Leaky integrate and fire neuronal model.

Parameters:: config (ALIFNeuronConfig | None)

config: ALIFNeuronConfig[source]#

soma: spark.nn.components.somas.leaky.AdaptiveLeakySoma[source]#

delays: spark.nn.components.delays.base.Delays[source]#

synapses: spark.nn.components.synapses.base.Synanpses[source]#

learning_rule: spark.nn.components.learning_rules.base.LearningRule[source]#

max_delay[source]#

inhibitory_rate[source]#

async_spikes[source]#

build(input_specs)[source]#

Build method.

Parameters:: input_specs (dict[str, spark.core.specs.InputSpec])

__call__(in_spikes)[source]#

Update neuron’s states and compute spikes.

Parameters:: in_spikes (spark.core.payloads.SpikeArray)
Return type:: spark.nn.neurons.NeuronOutput

class spark.nn.neurons.ALIFNeuronConfig(**kwargs)[source]#

Bases: spark.nn.neurons.NeuronConfig

ALIFNeuron configuration class.

max_delay: float[source]#

inhibitory_rate: float[source]#

async_spikes: bool[source]#

soma_config: spark.nn.components.somas.leaky.AdaptiveLeakySomaConfig[source]#

synapses_config: spark.nn.components.synapses.base.SynanpsesConfig[source]#

delays_config: spark.nn.components.delays.base.DelaysConfig[source]#

learning_rule_config: spark.nn.components.learning_rules.base.LearningRuleConfig[source]#