spark.nn.components.learning_rules.quadruplet_rule

spark.nn.components.learning_rules.quadruplet_rule#

Classes#

`QuadrupletRuleConfig`	QuadrupletRule configuration class.
`QuadrupletRule`	Quadruplet plasticy rule model.
`QuadrupletRuleTensorConfig`	QuadrupletRuleTensor configuration class.
`QuadrupletRuleTensor`	Quadruplet plasticy rule model (tensor).

Module Contents#

class spark.nn.components.learning_rules.quadruplet_rule.QuadrupletRuleConfig(__skip_validation__=False, **kwargs)[source]#

Bases: spark.nn.components.learning_rules.base.LearningRuleConfig

QuadrupletRule configuration class.

Parameters:: __skip_validation__ (bool)

pre_tau: float | jax.Array[source]#

post_tau: float | jax.Array[source]#

q_alpha: float | jax.Array[source]#

q_beta: float | jax.Array[source]#

q_gamma: float | jax.Array[source]#

q_delta: float | jax.Array[source]#

gamma: float | jax.Array[source]#

class spark.nn.components.learning_rules.quadruplet_rule.QuadrupletRule(config=None, **kwargs)[source]#

Bases: spark.nn.components.learning_rules.base.LearningRule

Quadruplet plasticy rule model.

Init:: pre_tau: float | jax.Array post_tau: float | jax.Array q_alpha: float | jax.Array q_beta: float | jax.Array q_gamma: float | jax.Array q_delta: float | jax.Array eta: float | jax.Array
Input:: modulation: FloatArray pre_spikes: SpikeArray post_spikes: SpikeArray kernel: FloatArray
Output:: kernel: FloatArray

Parameters:: config (QuadrupletRuleConfig | None)

config: QuadrupletRuleConfig[source]#

build(input_specs)[source]#

Build method.

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

reset()[source]#

Resets component state.

Return type:: None

__call__(modulation, pre_spikes, post_spikes, kernel)[source]#

Computes and returns the next kernel update.

Parameters:

modulation (spark.core.payloads.FloatArray)
pre_spikes (spark.core.payloads.SpikeArray)
post_spikes (spark.core.payloads.SpikeArray)
kernel (spark.core.payloads.FloatArray)

Return type:

spark.nn.components.learning_rules.base.LearningRuleOutput

class spark.nn.components.learning_rules.quadruplet_rule.QuadrupletRuleTensorConfig(__skip_validation__=False, **kwargs)[source]#

Bases: spark.nn.components.learning_rules.base.LearningRuleConfig

QuadrupletRuleTensor configuration class.

Parameters:: __skip_validation__ (bool)

pre_tau: tuple[float, float, float, float][source]#

post_tau: tuple[float, float, float, float][source]#

q_alpha: tuple[float, float, float, float][source]#

q_beta: tuple[float, float, float, float][source]#

q_gamma: tuple[float, float, float, float][source]#

q_delta: tuple[float, float, float, float][source]#

max_clip: tuple[float, float, float, float][source]#

eta: float[source]#

class spark.nn.components.learning_rules.quadruplet_rule.QuadrupletRuleTensor(config=None, **kwargs)[source]#

Bases: spark.nn.components.learning_rules.base.LearningRule

Quadruplet plasticy rule model (tensor).

Init:: pre_tau: float | jax.Array post_tau: float | jax.Array eta: float | jax.Array
Input:: modulation: FloatArray pre_spikes: SpikeArray post_spikes: SpikeArray kernel: FloatArray
Output:: kernel: FloatArray