This is the final project of my Machine Learning Course.
Original Dataset is from http://yann.lecun.com/exdb/mnist/ , including all four files of training and testing datasets.
The project aims to build a 10-class classifier that can recognize the handwritten digits using the data from the MNIST dataset. In MNIST dataset, each image is a 28 by 28 pixel square and a standard spit of the dataset is used to evaluate and compare models, where 60,000 images are available to train a model and a separate set of 10,000 images are used to test it. The models were built using multiple machine learning techniques in neural network, including DNN and CNN. The goal is to use the least amount of training data to achieve the highest possible testing accuracy at the meantime.