In this chapter, we will immerse ourselves in the world of machine learning (ML) and Core ML by working through what could be considered the 101 Core ML application. We will be using an image classification model to allow the user to point their iPhone at anything and have the app classify the most dominant object in the view. 

We will start off by first discussing the concept of convolutional neural networks (ConvNets or CNNs), a category of neural networks well suited to image classification, before jumping into implementation. Starting from a skeleton project, you will soon discover just how easy it is to integrate ML into your apps with the help of Core ML.

In this chapter, we will cover the following topics:

• Gaining some intuition on how machines understand images
• Building out the example application for this chapter
• Capturing photo frames and preprocessing them before passing them to the Core ML model
• Using the Core ML model to perform inference and interpreting the result