This project is a fulfillment to complete the Methods of Statistical Data Analysis postgraduate studies at AGH University of Science and Technology in Krakow, Poland.
In this project I compared several different Artificial Neural Network (ANN) architectures in terms of their accuracy in recognizing handwritten digits. The best performing neural network scored 99.6% accuracy on MNIST dataset which, when the model was submitted, was among the top 10% accuracies on Kaggle.
