How to build a simple neural network in 9 lines of Python code

[Gregory Ewing]

Steve D'Aprano wrote:
> It should be obvious that if you allow the use of external
> libraries that can contain arbitrary amounts of code, *without* counting that
> external code towards your measure of code complexity, you get a bogus
> measurement of code complexity.

Numpy isn't really doing a lot here, just saving you from
having to write some explicit loops. The code would be
maybe 2 or 3 times bigger at most without it.

What this example says to me is not so much how powerful
Python is, but how simple in essence neural networks are.

-- 
Greg