I understand that in order to add additional inputs to a CNN, e.g. in self driving, I can append the data to a flattened layer after the convolutions and before the fully connected layers.
However, a few things confuse me. In a paper the authors want to feed speed measurements into the driving network. Instead of just appending a normalized speed value, they first feed it into several FC layers. Why would they do that? What kind of features could you extract from a single real value? Could there be another reason?
(p. 3, paper 1)
Part two of my question is: In another paper, information about the turn signal is appended to a layer as one-hot encoding. The authors talk about how that didn’t work due to vanishing weights (not gradients). So they scaled weights by a constant factor. What do they mean by vanishing weights and how do I scale weights (e.g. in PyTorch)?
(p. 6, paper 2)