>>nyrikk+(OP)
Man that "Unreasonable Effectiveness of ..." pattern is getting a bit overused. With the original paper [1] you could still say that there really is some deeply philosophical mystery. But they now slap that on everything.
>>ngruhn+0o
TIL. I am not from an engineering/physics background so for me the original Unreasonable Effectiveness paper was Karpathy’s blog post about RNNs.