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: torch.Tensor, s: norse.torch.functional.lsnn.LSNNFeedForwardState, p: norse.torch.functional.lsnn.LSNNParameters = LSNNParameters(tau_syn_inv=tensor(200.), tau_mem_inv=tensor(100.), tau_adapt_inv=tensor(0.0012), v_leak=tensor(0.), v_th=tensor(1.), v_reset=tensor(0.), beta=tensor(1.8000), method='super', alpha=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