Allow slayer norms to use parameters

[Gavinator98]

User story

As a user, I want to modify the arguments to slayer neuron norms.
The neuron norms provide arguments to adjust momentum and other parameters:

lava-dl/src/lava/lib/dl/slayer/neuron/norm.py

Line 36 in 543efaa

def __init__(self, num_features=None, momentum=0.1, pre_hook_fx=None):

However, when used the neuron calls the constructor with no arguments:

lava-dl/src/lava/lib/dl/slayer/neuron/base.py

Line 146 in 543efaa

self.norm = norm()

As a workaround it might be possible to use a lambda function as the norm argument:

params = {
    "norm": lambda x: slayer.neuron.norm.MeanOnlyBatchNorm(momentum=0.2)
}

[PhilippPlank]

Thank you for this suggestion. @bamsumit Could you take a look, when you find some time :)

[bamsumit]

@Gavinator98 The intended usage pattern is to call a lambda like you mention. This is by design because the norm could have other signatures and therefore cannot be known in advance.