> We argue complexity conceals underlying regularity, and that deep learning will indeed admit a scientific theory

That would be amazing, but personally I’m skeptical.

There is an analogy with statistical mechanics. It's not crazy.

	▲	wwarner an hour ago \| parent [-]
		Sane & interesting enough to have been disproven, by Boaz Barak iirc. Maybe not surprising since simulated annealing never achieved the results of gradient descent + backprop.