This repository contains my implementation of a simple feedforward neural network from scratch in numpy to improve my understanding of backpropagation, optimization, and other aspects of Deep Learning.
Make sure you have the following libraries installed.
pip==22.3.1
setuptools==65.6.0
wheel==0.38.4
numpy==1.23.5
scikit-learn==1.2.0
matplotlib==3.6.2
emnist==0.0
You can then download the repository as .zip file from GitHub directly or pull via git.
An end to end training on MNIST is performed in tests_e2e/backward_pass_large.py.