norse.torch.functional.lsnn_feed_forward_adjoint_step

norse.torch.functional.lsnn_feed_forward_adjoint_step#

norse.torch.functional.lsnn_feed_forward_adjoint_step(input: Tensor, s: 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)[source]#

Implementes a single euler forward and adjoint backward step of a lif neuron with adaptive threshhold and current based exponential synapses.

Parameters:

input (torch.Tensor): input spikes from other cells v (torch.Tensor): membrane voltage state of this cell i (torch.Tensor): synaptic input current state of this cell b (torch.Tensor): state of the adaptation variable input_weights (torch.Tensor): synaptic weights for input spikes recurrent_weights (torch.Tensor): recurrent weights for recurrent spikes p (LSNNParameters): parameters to use for the lsnn unit dt (torch.Tensor): integration timestep