spark.nn.components.delays.n2n_delays

spark.nn.components.delays.n2n_delays#

Classes#

`N2NDelaysConfig`	N2NDelays configuration class.
`N2NDelays`	Data structure for spike storage and retrival for efficient neuron to neuron spike delay implementation.

Module Contents#

class spark.nn.components.delays.n2n_delays.N2NDelaysConfig(__skip_validation__=False, **kwargs)[source]#

Bases: spark.nn.components.delays.n_delays.NDelaysConfig

N2NDelays configuration class.

Parameters:: __skip_validation__ (bool)

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

class spark.nn.components.delays.n2n_delays.N2NDelays(config=None, **kwargs)[source]#

Bases: spark.nn.components.delays.base.Delays

Data structure for spike storage and retrival for efficient neuron to neuron spike delay implementation. This synaptic delay model implements specific conduction delays between specific neruons. Example: Neuron A fires and neuron B, C, and D listens to A; neuron B recieves A’s spikes I timesteps later,

neuron C recieves A’s spikes J timesteps later and neuron D recieves A’s spikes K timesteps later.

Init:: units: tuple[int, …] max_delay: float delays: jnp.ndarray | Initializer
Input:: in_spikes: SpikeArray
Output:: out_spikes: SpikeArray