norse.torch.functional.lif_feed_forward_adjoint_step(input: Tensor, s: LIFFeedForwardState, p: LIFParameters = (tensor(200.), tensor(100.), tensor(0.), tensor(1.), tensor(0.), 'super', tensor(100.)), dt: float = 0.001) Tuple[Tensor, LIFFeedForwardState][source]#

Implementes a single euler forward and adjoint backward step of a leaky integrate and fire neuron with current based exponential synapses.


input (torch.Tensor): input spikes from other cells s (LIFFeedForwardState): state of leaky integrate and fire neuron p (LIFParameters): leaky integrate and fire parameters dt (float): time step of integration