norse.torch.functional.signed_poisson_encode_step

norse.torch.functional.signed_poisson_encode_step(input_values: torch.Tensor, f_max: float = 1000, dt: float = 0.001)torch.Tensor[source]

Creates a poisson distributed signed spike vector, when

Parameters:

input_values (torch.Tensor): Input data tensor with values assumed to be in the interval [-1,1]. f_max (float): Maximal frequency (in Hertz) which will be emitted. dt (float): Integration time step (should coincide with the integration time step used in the model)

Returns:

A tensor containing values in {-1,0,1}.