norse.torch.functional.lsnn_feed_forward_step#

norse.torch.functional.lsnn_feed_forward_step(input_tensor: Tensor, state: LSNNFeedForwardState, p: LSNNParameters = (tensor(200.), tensor(100.), tensor(0.0012), tensor(0.), tensor(1.), tensor(0.), tensor(1.8000), 'super', 100.0), dt: float = 0.001) → Tuple[Tensor, LSNNFeedForwardState][source]#

Euler integration step for LIF Neuron with threshold adaptation. More specifically it implements one integration step of the following ODE

$$\text{begin{split} ended with end{align*}}$$

together with the jump condition

$$z=\mathrm{\Theta }(v-v_{\text{th}}+b)$$

and transition equations

$$\begin{array}{r}\begin{array}{rl}v& =(1-z)v+z{v}_{\text{reset}}\\ i& =i+\text{input}\\ b& =b+\beta z\end{array}\end{array}$$

Parameters:

input_tensor (torch.Tensor): the input spikes at the current time step s (LSNNFeedForwardState): current state of the lsnn unit p (LSNNParameters): parameters of the lsnn unit dt (float): Integration timestep to use