I decided to solve FizzBuzz like a mathematician would aka the most obnoxious way I could imagine. This is my gift to you.https://gist.github.com/Gorcenski/f03c834696cb94768561283cfb9b82b2 …
-
-
It’s easy to test against, it pretty quickly shows if you have e.g. a configuration issue, and creative solutions are good mental exercises in otherwise tedious work
Show this thread -
But what’s relevant here is that there are a few concepts that are used widely in data science and it brings them from an abstract notion to something concrete. In this case, cyclic behavior has a natural relation to polynomials and to 1D vector convolutions.
Show this thread -
1-D convolutions neural networks use such convolutions, and they’re being used for text process and other applications where recurrent neural nets have found some success. The underlying relations become a little more clear when you see it in this light.
Show this thread -
And if you take it a step further and recognize that discrete convolutions are related to joint probability distribution functions, then all of a sudden the probabilistic nature of how neural networks work emerges like truth from the well.
Show this thread
End of conversation
New conversation -
-
-
The "shit" part is one of those "it depends" things. We use exercises at this level to explore a candidate's thought process for emerging a design via microtests. We go slow with a lot of interaction to discuss design choices. We want a simple problem that won't be a distraction.
-
And based on your thread, my guess is it would be a lot of fun to work with you.
End of conversation
New conversation -
-
-
I like it for trying out new languages, esp when trying to learn best way for that language to do things
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Interview: Please use a ML package of your choice and teach it to recognize a correct fizzbuzz algorithm with 90% success rate. Muhahahahaha... You have 10 minutes.
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.