spark.nn.brain

Classes

BrainMeta	Brain metaclass.
BrainConfig	Configuration class for Brain's.
Brain	Brain model.

Module Contents

class spark.nn.brain.BrainMeta

Bases: spark.core.module.SparkMeta

Brain metaclass.

class spark.nn.brain.BrainConfig(__skip_validation__=False, **kwargs)

Bases: spark.core.config.BaseSparkConfig

Configuration class for Brain’s.

Parameters:

__skip_validation__ (bool)

input_map: dict[str, spark.core.specs.PortSpecs]

output_map: dict[str, dict]

modules_map: dict[str, spark.core.specs.ModuleSpecs]

validate(is_partial=False, errors=None, current_path=['brain'])

Validates all fields in the configuration class.

Parameters:

• is_partial (bool)

• errors (list | None)

• current_path (list[str])

Return type:

dict[str] | None

refresh_seeds()

Utility method to recompute all seed variables within the SparkConfig. Useful when creating several populations from the same config.

class spark.nn.brain.Brain(config=None, **kwargs)

Bases: spark.core.module.SparkModule

Brain model.

A brain is a pipeline object used to represent and coordinate a collection of neurons and interfaces. This implementation relies on a cache system to simplify parallel computations; every timestep all the modules in the Brain read from the cache, update its internal state and update the cache state. Note that this introduces a small latency between elements of the brain, which for most cases is negligible, and for such a reason it is recommended that only full neuron models and interfaces are used within a Brain.

Parameters:

config (BrainConfig)

config: BrainConfig

resolve_initialization_order()

Resolves the initialization order of the modules.

build(input_specs)

Build method.

Parameters:

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

reset()

Resets all the modules to its initial state.

__call__(**inputs)

Update brain’s states.

Parameters:

inputs (spark.core.payloads.SparkPayload)

Return type:

dict[str, spark.core.payloads.SparkPayload]

get_spikes_from_cache()

Collect the brain’s spikes.

Return type:

dict