gnipgnip

Exercise in dealing with such "Exhibit A"'s:

> Pythagoras' school provided the earliest documented proof of the theorem, but the result was possibly known as early as 3000 BC.

Actually there is no known evidence Pythagoras or his school had any relation to the theorem. Much of it is word-of-mouth legend (and even then not particularly informative).

It's amusing when the same people accept legends from Europe as canonical, while treating similar historical data in India as literally non-existent.

> Don't be too enamored. These are fairly standard right wing talking points in India. From his comments on Gandhi and Pythagoras one can easily infer that he is a supporter of Narendra Modi and Hindu supremacy.

> As for Gandhi, he grew up in a strictly birth based hierarchical society and he pretty much accepted social and racial hierarchies until his thoughts evolved circa 1913. Most of Gandhi's racist quotes come from before 1910.

I guess the Native Americans too were "supremacists". How about the Bantus, don't forget them, man! ... These narratives get mind-numbingly boring; much as it does to hear of the BJP as some great establishment challengers. Eesh, don't you sheep read anything other than the Hindu's editorials ? In any case, this has typically been the talking point of the status quo-ists and pro-establishment ones for .. what 300 years ?

I'd not keep my hopes up with such creatures though since they have neither the afflictions of reading nor of reason. Social creatures will exploit the status-quo for maximum gain, and anyone who claims we (even in the occident) don't live in a hierarchical society are naive fools not worth arguing with.

Wow! How much do people manage to generally save in Japan as opposed to SF ?

It's not clear that it will change every industry; it'll definitely lead to great job losses in certain fields with the oncoming ADAS boom.

I can't think of other areas where it'll have such a big impact. Robotics (other than Automated driving) has decades more left to fulfill its promise.

Oh really?

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).

Don't need to when you read papers.

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.

Yeah, nature is concerned with our petty lives and freedoms.

You may as well ask:

"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.

[2]　acharya: "Guru" lit. he who walks the path

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...).

Sadly you can only share pickleable objects in python multiprocessing.

Clearly you've never run any of the object detection nets. State of the art is still 70 fps on Pascal for a 300x300 image.