this was a BIG hurdle for me when spinning up w/ ML basics - the difference between 18th-century-looking math notations and how one might think it out code-wise drove me up. a. wall.https://twitter.com/jeremyphoward/status/1233011836057870338 …
-
This Tweet is unavailable.
That's a very interesting point. I would say though that the python code is abstracting this hairy detail away and you don't normally think of numerical errors like this unless you're really getting into the nitty/gritty of computational correctness.
-
-
This one is interesting as it uses math to get around a numeric floating point issue. Here, I point out why both code & maths are problematic all things considered. (Code is not general, ambigious & Maths leaves too much unsaid)https://twitter.com/sir_deenicus/status/1233869696157540353 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.