A simple 2D CNN for MNIST digit recognition – Towards Data Science

Convolutional Neural Networks (CNNs) are the current state-of-art architecture for image classification task. Whether it is facial recognition, self driving cars or object detection, CNNs are being used everywhere. In this post, a simple 2-D Convolutional Neural Network (CNN) model is designed using keras with tensorflow backend for the well known MNIST digit recognition task. The data set used here is MNIST dataset as mentioned above. The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits (0 to 9).