# Backpropagation for noobs

I am trying to understand neural networks and how they work, by programming my own one from scratch in nodejs. Currently, i managed to build a network, that has weights, layers and neurons. I also understood what an activation function is and i am using the sigmoid function.

I've now come to the point of back propagation with the gradient descent algorithm. My Problem is, that i only know 10th grade Math and every tutorial/explanation i managed to find, uses complex functions and math which i cannot manage to understand.

I would really like to finish this project and get back propagation to work, so if someone could explain me how to use the back propagation without using too complex math (e, derivatives, functions, etc.) or explaining the complex math it would be greatly appreciated.

My source Code: https://gitlab.com/milan44/node (Training is happening in Network.prototype.train)

• (+1) without 'complex' math backprop cannot be implemented. You will have to get a handle on the complex maths somehow. – naive Feb 26 '19 at 11:17