Introduction

So far, we have only been working with numbers and text. In this chapter, we will learn how to use machine learning to decode images and extract meaningful information, such as the type of object present in an image, or the number written in an image. Have you ever stopped to think about how our brains interpret the images they receive from our eyes? After millions of years of evolution, our brains have become highly efficient and accurate at recognizing objects and patterns from the images they get from our eyes. We have been able to replicate the function of our eyes using cameras, but making computers recognize patterns and objects in images is a really tough job. The field associated with understanding what is present in images is known as computer vision. The field of computer vision has witnessed tremendous research and advancements in the past few years. The introduction of Convoluted Neural Networks (CNNs) and the ability to train neural networks on GPUs were the biggest...