This repo contains notebooks demonstrating hand-written digit recognition with various network architectures, including multi-layer perceptron (MLP) and convolutional neural network (CNN).
The dataset is the famous MNIST dataset consisting of 60,000 training and 10,000 test images, each 28x28 pixels.
Create and activate a new python environment and then run this line to install all the required dependencies:
pip install -r requirements.txt
Then open the Jupyter notebooks and run them top-to-bottom.