Handwritten Digit Classifier Using Adversarial Learning

In this chapter, we will build an Android application that identifies free handwriting and classifies a number using adversarial learning. We will use the MNIST dataset for the digit classification. We will look into the basics of Generative Adversarial Networks (GANs).

In this chapter, we will take a closer look at the following: 

• GAN basics
• Understanding the Modified National Institute of Standards and Technology (MNIST) database
• Building a classifier
• Building an Android application

The code for this application can be found at https://github.com/intrepidkarthi/MLmobileapps/tree/master/Chapter6. and https://github.com/PacktPublishing/Machine-Learning-Projects-for-Mobile-Applications.