norse.torch.functional.lif_box.lif_box_feed_forward_step

norse.torch.functional.lif_box.lif_box_feed_forward_step

norse.torch.functional.lif_box.lif_box_feed_forward_step(input_tensor: torch.Tensor, state: norse.torch.functional.lif_box.LIFBoxFeedForwardState, p: norse.torch.functional.lif_box.LIFBoxParameters = LIFBoxParameters(tau_mem_inv=tensor(100.), v_leak=tensor(0.), v_th=tensor(1.), v_reset=tensor(0.), method='super', alpha=tensor(100.)), dt: float = 0.001) Tuple[torch.Tensor, norse.torch.functional.lif_box.LIFBoxFeedForwardState][source]

Computes a single euler-integration step for a lif neuron-model without current terms. It takes as input the input current as generated by an arbitrary torch module or function. More specifically it implements one integration step of the following ODE

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

together with the jump condition

\[z = \Theta(v - v_{\text{th}})\]

and transition equations

\[v = (1-z) v + z v_{\text{reset}}\]
Parameters:

input_tensor (torch.Tensor): the input spikes at the current time step state (LIFBoxFeedForwardState): current state of the LIF neuron p (LIFBoxParameters): parameters of a leaky integrate and fire neuron dt (float): Integration timestep to use