norse.torch.functional.leaky_integrator_box

Leaky integrators describe a leaky neuron membrane that integrates incoming currents over time, but never spikes. In other words, the neuron adds up incoming input current, while leaking out some of it in every timestep.

\[\begin{align*} \dot{v} &= 1/\tau_{\text{mem}} (v_{\text{leak}} - v + i) \end{align*}\]

This module differs from the `leaky integrator`_ module by excluding the current term, so any inputs will have immediate, stepwise, impacts on the voltage (hence the “box”).

More information can be found on Wikipedia or in the book *Neuron Dynamics* by W. Gerstner et al., freely available online.

Functions

li_box_feed_forward_step(input_tensor, state)
li_box_step(input_spikes, state, input_weights)	Single euler integration step of a leaky-integrator without a current term.

Classes

LIBoxParameters([tau_mem_inv, v_leak])	Parameters of a leaky integrator without a current term
LIBoxState(v)	State of a leaky-integrator without a current term