jaxsnn.event.solver.next_finder

Classes

BaseState()

Base class for all neuron states across paradigms

Event(time, idx)

Functions

jaxsnn.event.solver.next_finder.next_event(solver: Callable[[StateT, float], jaxsnn.event.types.Spike], neuron_state: jaxsnn.base.types.BaseState, time: jax.Array, t_max: float) → jaxsnn.event.types.Event

Wraps a root solver to provide a cleaner API for returning next event.

Parameters

  • solver – The actual root solver function.

  • neuron_state – The state of the neurons.

  • time – Current simulation time.

  • t_max – Maximum time of the simulation.

Returns

Event object representing the spike which will occur next.

jaxsnn.event.solver.next_finder.next_queue(known_spikes: jaxsnn.event.types.Event, layer_start: int, neuron_state: jaxsnn.base.types.BaseState, time: float, t_max: float) → jaxsnn.event.types.Event

Return the upcoming spike when training with hardware-in-the-loop.

When working with the BSS-2 system, we have all the spikes in advance and need to find the index and time of the next event. When the hardware spikes are bound to this function with functools.partial, it has the same API as next_event.

Parameters

  • known_spikes – All spikes from BSS-2.

  • layer_start – Start index of the current layer.

  • neuron_state – The state of the neurons (unused).

  • time – Current simulation time.

  • t_max – Maximum simulation time.

Returns

Event object representing the spike which will occur next in the layer.