top | item 37228805

(no title)

scottmas | 2 years ago

It’s inherent to their architecture. Feedforward deep neural networks are effectively massive piecewise linear functions. Unless I’m missing something, it’s literally impossible for any NN, no matter how large or how much data they’re trained on to give accurate out-of-training-data-bounds predictions for even a ridiculously simple function like x^2.

discuss

order

No comments yet.