There are a lot of options of what to measure with Pennylane but I am not sure which observable to measure. Does it make sense to measure the mean position quadrature operator \langle \hat X \rangle, mean momentum quadrature opertator \langle \hat P \rangle or the mean photonic number \langle \hat n \rangle with a photonic computer when making a measurement for machine learning needs?

An example of a layer I am referring to:

```
wires = 2
n_quantum_layers = 1
dev = qml.device("strawberryfields.fock", wires=wires, cutoff_dim=15)
@qml.qnode(dev)
def layer(inputs, w0, w1, w2, w3, w4, w5, w6, w7, w8, w9, w10):
qml.templates.DisplacementEmbedding(inputs, wires=range(wires))
qml.templates.CVNeuralNetLayers(w0, w1, w2, w3, w4, w5, w6, w7, w8, w9, w10, wires=range(wires))
return [qml.expval(qml.X(wires=i)) for i in range(wires)]
```

Since the fock states are a natural encoding strategy, wouldn’t it be better to measure the \langle \hat n \rangle here? On the other hand, the \langle \hat n \rangle is limited in possible values. So perhaps that is why \langle \hat X \rangle or \langle \hat P \rangle is better to use?