MNIST_NeuralNetwork
Classifying the MNIST data set with neural networks
Personal educational project, built in order to understand how neural networks function and how backpropogation works. The model used in this project is a simple multilayer perceptron. The NeuralNetwork class is set up so that various configurations can be tried with different numbers of hidden layers, different numbers of hidden layer nodes, and different learning rates.
References: http://neuralnetworksanddeeplearning.com/chap2.html https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/