norse.torch.functional.lif_refrac_feed_forward_adjoint_step

norse.torch.functional.lif_refrac_feed_forward_adjoint_step#

norse.torch.functional.lif_refrac_feed_forward_adjoint_step(input: Tensor, s: LIFRefracFeedForwardState, p: LIFRefracParameters = ((tensor(200.), tensor(100.), tensor(0.), tensor(1.), tensor(0.), 'super', tensor(100.)), tensor(5.)), dt: float = 0.001) Tuple[Tensor, LIFRefracFeedForwardState][source]#

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.