norse.torch.functional.lif_adex.LIFAdExParameters

norse.torch.functional.lif_adex.LIFAdExParameters#

class norse.torch.functional.lif_adex.LIFAdExParameters(adaptation_current: Tensor = tensor(4), adaptation_spike: Tensor = tensor(0.0200), delta_T: Tensor = tensor(0.5000), tau_ada_inv: Tensor = tensor(2.), tau_syn_inv: Tensor = tensor(200.), tau_mem_inv: Tensor = tensor(100.), v_leak: Tensor = tensor(0.), v_th: Tensor = tensor(1.), v_reset: Tensor = tensor(0.), method: str = 'super', alpha: float = 100.0)[source]#

Parametrization of an Adaptive Exponential Leaky Integrate and Fire neuron

Default values from NeuralEnsemble/PyNN

Parameters:

adaptation_current (torch.Tensor): adaptation coupling parameter in nS adaptation_spike (torch.Tensor): spike triggered adaptation parameter in nA delta_T (torch.Tensor): sharpness or speed of the exponential growth in mV tau_syn_inv (torch.Tensor): inverse adaptation time

constant (\(1/\tau_\text{ada}\)) in 1/ms

tau_syn_inv (torch.Tensor): inverse synaptic time

constant (\(1/\tau_\text{syn}\)) in 1/ms

tau_mem_inv (torch.Tensor): inverse membrane time

constant (\(1/\tau_\text{mem}\)) in 1/ms

v_leak (torch.Tensor): leak potential in mV v_th (torch.Tensor): threshold potential in mV v_reset (torch.Tensor): reset potential in mV method (str): method to determine the spike threshold

(relevant for surrogate gradients)

alpha (float): hyper parameter to use in surrogate gradient computation

__init__()#

Methods

__init__()

count(value, /)

Return number of occurrences of value.

index(value[, start, stop])

Return first index of value.

Attributes

adaptation_current

Alias for field number 0

adaptation_spike

Alias for field number 1

alpha

Alias for field number 10

delta_T

Alias for field number 2

method

Alias for field number 9

tau_ada_inv

Alias for field number 3

tau_mem_inv

Alias for field number 5

tau_syn_inv

Alias for field number 4

v_leak

Alias for field number 6

v_reset

Alias for field number 8

v_th

Alias for field number 7