So now, we have a clear sense of why we need to do it and how we can. From now, we're going to dive deeper in details. But before realizing if it works, let's see how it works. Well, each PPN is fed by two streams (O and S); the first is directed to the InAdapter, and the latter bypasses InAdapter to MLP. Let's see the PPN in more detail: In Figure 4. We can see that InAdapter transforms output o (output of previous module (in this figure, it is NLU)) to vector v, and then MLP converts the vector v to another vector v (you can see some numbers cannot be encoded so they'll copy to v) These equations are all we need to understand what's going on in PPNs.