Back-propagation from scratch in python
-----backpropagation algorithm and tested it in the following 2 class problem called the Star problem.
----BP.py-------
x1 x2 d 1 0 1 0 1 1 -1 0 1 0 -1 1 0.5 0.5 0 -.5 0.5 0 0.5 -.5 0 -.5 -.5 0
------A.py--------
Created a letter A (see figure below) with a two hidden layer MLP with signum units (threshold nonlinearity)