On Wed, 28 Jun 2017 05:34 am, Marko Rauhamaa wrote: > John Ladasky <john_lada...@sbcglobal.net>: >> OK, that's cheating a bit, using Numpy. It's a nice little program, >> but it leverages a huge, powerful library. > > What would *not* be cheating? A language without a library would be > dead.
Its not really nine lines of Python. It's nine lines of Python, to call a library of many thousands of lines of C, Fortran and Python. And its not really a neural *network* as such, more like just a single neuron. Starting from scratch with just the Python language and standard library, no external third party code, how quickly can you write a neural network? I think the answer is probably a wee bit more than "nine lines". -- Steve “Cheer up,” they said, “things could be worse.” So I cheered up, and sure enough, things got worse. -- https://mail.python.org/mailman/listinfo/python-list
