[wodenokoto]

I'm surprised about the NN that memorize the data. I'd imagined there would not be enough units to memorize everything.

But if we have a network that has essentially memorized a random dataset, how is it functionally different from a nearest neighbor algorithm?

[Eridrus]

And there we have the million dollar question that people are still struggling to answer: why do neural nets work, when existing theory says they should not?