A simple, exploratory study on the use of Deep Neural Networks (DNNs) with Keras framework (Tensorflow background) for a simple handwritten number image classification task. This project was primarily made with the purpose of learning and getting familiar with Multi-layered Perceptrons, training and performance testing in Keras framework, which efficiently streamlines its implementation with intuitive, simple-to-use functional APIs. This eliminates the need of managing computational graphs in Tensorflow and allows us to easily play with the Neural Network Architecture.
We have used the renowned MNIST Handwritten Digits Dataset containing 60,000 train samples and 10,000 test samples of 28x28 grayscale images depicting numerical digits written by a huge number of human subjects.