def __init__(
self,
seq_length: int,
parameters: lif.LIFParameters = lif.LIFParameters(),
dt: float = 0.001,
):
"""
Encodes input currents as fixed (constant) voltage currents, and simulates the spikes that
occur during a number of timesteps/iterations (seq_length).
Example:
>>> data = torch.tensor([2, 4, 8, 16])
>>> seq_length = 2 # Simulate two iterations
>>> constant_current_lif_encode(data, seq_length)
(tensor([[0.2000, 0.4000, 0.8000, 0.0000], # State in terms of membrane voltage
[0.3800, 0.7600, 0.0000, 0.0000]]),
tensor([[0., 0., 0., 1.], # Spikes for each iteration
[0., 0., 1., 1.]]))
Parameters:
seq_length (int): The number of iterations to simulate
parameters (LIFParameters): Initial neuron parameters. Defaults to zero.
dt (float): Time delta between simulation steps
"""
super(ConstantCurrentLIFEncoder, self).__init__()
self.seq_length = seq_length
self.parameters = parameters
self.dt = dt
def __init__(self, seq_length, parameters=lif.LIFParameters(), dt=0.001):
super(SpikeLatencyLIFEncoder, self).__init__()
self.seq_length = seq_length
self.parameters = parameters
self.dt = dt