I have been working to understand the backpropogation algorithm, and I finally think I have gained some grasp of the concept. So I have now begun trying to implement the algorithm, and have so far had no success. I have built a toy neural network that can randomly initialize weights and biases and then feed-forward. If possible, I would like to see a full implementation that I can reverse engineer.
In my GitHub page is a simple Neural Network class and a sigmoid and vector mapping function I use. Any modification to a copy of the code is fine, it's not perfect, additionally any learning resources are always appreciated. Thanks in advance.
** Note I am looking to implement the MSE algorithm with gradient descent and the chain rule.
** The code is in Python (Probably should have mentioned that)