The mathematician in me has kept me from jumping into deep learning before I understand the mathematical and statistical underpinnings of the algorithms involved. Looking forward to reading through the latest book out by mit press and giving things a whirl with Keras which I've heard so much about.
The only "math" in deep learning is given by reverse mode AD (or if you're into fancy stuff, "efficient computing of pullbacks"). The rest of it plain old hacking, and empirical tricks with the occasional variational doodads.
You clearly also haven't read many of the papers it cites.
I would say one weakness of the book is that parts of it are too much like a survey of the papers in a subfield. Another is that it is very heavy on theory and light on practice (e.g., no exercises.)
Pray tell me, oh self-conceited one, what I missed that is both in actual use and in that book ? For things outside this set, you'd not read this book anyway; nor would such things be called "deep learning" (other than may be RBMs).
