MNIST-Digit-Classification

A neural network model that uses MNIST dataset of handwritten digits and classifies them accordingly.

My approach to this problem was by using 2 methods:

1. Fully Connected Neural Network
2. Convolutional Neural Network

Fully Connected Neural Network

First construct a neural network consisting of two fully connected layers and apply this to the digit classification task. This network will ultimately output a probability over the 10 digit(0-9).

Convolutional Neural Network

Convolutional neural networks (CNN) are well-suited for a variety of tasks in computer vision, and have near-perfect accuracies on the MNIST dataset. First construct model composed of two convolutional layers and pooling layers, followed by fully connected layers mentioned above, and output a probability over the 10 digit(0-9).