This is a simple tutorial to implement a feedforward neural network from scratch in Python in under 150 lines using only Python standard libraries. The training technique is using backpropagation with learning and momentum rate parameters.
Refer to neural-network-tutorial.ipynb for the tutorial. If you want to jump straight to the code, code/backprop_network_uc.py is the uncommented code and code/backprop_network.py is the commented code.