norse.torch.functional.lif_refrac_feed_forward_adjoint_step

norse.torch.functional.lif_refrac_feed_forward_adjoint_step(input: torch.Tensor, s: norse.torch.functional.lif_refrac.LIFRefracFeedForwardState, p: norse.torch.functional.lif_refrac.LIFRefracParameters = LIFRefracParameters(lif=LIFParameters(tau_syn_inv=tensor(200.), tau_mem_inv=tensor(100.), v_leak=tensor(0.), v_th=tensor(1.), v_reset=tensor(0.), method='super', alpha=tensor(100.)), rho_reset=tensor(5.)), dt: float = 0.001) → Tuple[torch.Tensor, norse.torch.functional.lif_refrac.LIFRefracFeedForwardState]

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