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).
"Why are parish school students so Christian". This is not to say that they viscerally believe in these qualities... oh nooo. It's just that if you want to play the game, you optimize for the environment (I may have picked that up from Alan Watts). Simple RL really.
Idiots, and loudmouths, on the other hand will get ostracized and have pots broken over their heads; one shouldn't be surprised if something one writes on a public forum will get one fired from school/work (may have happened to the younger me once). This is not the depressing thing though - no the depressing thing is that the rules of the game are never explained clearly. In this sense, the Western liberal dogma is essentially the Christian one of grovelling expiation. You know... one can be as bad in action, but words and "belief", expressed tirelessly over and over, are key to salvation [1]. Terrible, terrible messaging to the naive younglings.
This probably explains why some (generally poor) idiots in the Midwest send tons of money to "harvest Asia in the name of Christ" (well atleast to those in power), while jumping up an down to keep these "loved" people away from their neighborhood. Then there is the New Age movement, "meditating" and "yoga-ing" for "peace" "health" and "environment" (and lots of greens), while showing total disdain for the path [2]... Namast.. No, fk you!
All this facade gets really really tiring.
[1] The laity in much of Asia believe in very similar things to be fair... although they don't get bonked on the head with a book everytime they are out of line.
Considering the glut of neural network libraries, it'd be useful if there were some blurb about what makes this "special".
To clarify myself, "what niche does this belong to". Caffe for instance remains (to the misery of people like me) the standard library on which reference CNNs are implemented (other than that little pony's YOLO :P).
Tensorflow/MXnet/Chainer/Torch have nice dynamic interfaces... but basically are doing the same thing underneath (calling cuDNN/GEMM), and have the backing of well-known researchers/big corporations (maybe not Chainer...).
A little hacky, yes, but extremely effective. I wrote an image processing application for somewhat large time-series datasets (> 1TB) on Linux which took liberal advantage of these details to run very nicely on v2 Xeon processors. It also worked quite well for GUIs which interacted with the datasets.
Sometimes worth it, but often not. The ability to do shared-memory multi-threading is one of the things that tempts me away from Python. Message passing is great and all, but sometimes you want your messages to be passing around control of a shared 4GB data structure, instead of trying to copy it.
To be fair, the Wikipedia sites for these languages barely have any content. Of those that do exist most articles are essentially 2-line blurbs. These languages are essentially dead for all practical purposes.
I'm not going to waterdown my analysis for some two bit politically correct occidentals and "hyper-nationalist" orientals.
A large fraction of Indian children will be illiterate in these "thriving" languages in the coming decades, with "zero" monetary loss. Not living is death, and they haven't been alive for a long time - I can neither get any Govt. services in my mother tongues, nor can get the laws done by the colonial state in Delhi.
A zombie is not alive IMO. If Indians wish to parlay their tongues for money, it's upto them. I for one will not deceive myself. We are going to be part of the borg that is the Anglosphere in less than 3-4 generations.
gnipgnip is first of all projecting, according to his analysis, Indians will stop talking local languages and adopt English and in 80 years its all over, India is an English speaking country, the flaw in that logic. The main problem is Indians do entertain themselves in their native languages, yes, many languages spoken by smaller groups of people are certainly under threat, but languages with currently massive footprints like Hindi, Telugu, Bengali etc. ain't going any where 80 years from now.
A language that is spoken by 80 million people is not dead, and is not dying. The colonial two-step when coming to languages existed for a long time and its just matter of time, people with help of machine learning will provide support in multiple languages etc.
For much large part of Mughal period the court language was Farsi, but Hindi/Urdu survived, you are underestimating the ability of people to straddle multiple languages. For many Indians its just a necessity.
Language shift occurs when mothers stop talking to their infants in the language. Not being able to access government services in the language may indicate a decline in the language's vitality, in its prestige and influence, but it is a long, long way from language "death".
