top | item 36679105

(no title)

e-neko | 2 years ago

if they're wrong, they don't work.

discuss

order

swexbe|2 years ago

If my BST implementation isn't sorted, it also doesn't work.

amelius|2 years ago

The difference is that you can reason about why it didn't work.

With deep learning models not so. They are too big to reason about in the same sense as your BST algorithm.

Hence, you need a scientific approach to construct them. I.e., with lots of experimenting, hypotheses, etc.

ethanbond|2 years ago

Same is true of a bridge or a combustion engine though?