[tinderliker]

>On some level, I suspect that Deep Learning being so trendy tweaked a little bit of contrarian in me, and I still have a little bit of a reflexive bias against “throw everything at the NN and let it sort it out!”

I am the same kind of person. But when John Carmack approaches this with scepticism and concludes that it is indeed not over-hyped, I guess its worth learning after all!

CS231N, here I come.

[tail-recursion]

He never said it is not over-hyped. Most people who work in the field think it is over-hyped.

[ryandrake]

I admit to having the same grouchy thoughts about machine learning and AI: When is this fad going to blow over and we can all get back to writing deterministic programs instead of collecting data and training models, or whatever it is this new breed is doing? Might be time to rethink and revive my curiosity.