Wide and Deep Learning: Better Together with TensorFlow

I'm curious, is it possible to train a model and send that model to a raspberry pi or something to make something like this realistic to use? Then take the results from the raspberry pi, send them elsewhere to be trained into the model? and repeat?

I don't know if I missed it, but I would have liked to have seen a performance/accuracy comparison between wide+deep learning and a simple ensemble between wide and deep models. The advantage to having 2 separate models is that you could use just one or the other if something went wrong, or if you needed to make a faster prediction (i.e. when the escalator breaks, you get stairs).

I am about to catch a flight, so I am unable to do anything better than skimming the post and paper. But isn't this just the good old feature embeddings coupled with learnt features that have been around for several years by now?

Can anyone give more examples of specific problems this could solve?