As someone who has read a lot of implementing neural networks from articles, the massive problem with all of them is that they import numpy. You may think that it is silly to reimplement the matrix math but with out that part of the code, you can't easily port it to other languages/microcontrollers/microwaves/badgers.<p>It's a legitimately valid part of machine learning, and its not easy to do for novices.<p>And I need help putting it on my badger damn it!