After covering the basics and the intuition/motivation behind Convolution Neural Networks (CNNs), we are going to demonstrate this on one of the most popular datasets available for object detection. We'll also see how the initial layers of the CNN get very basic features about our objects, but the final convolutional layers will get more semantic-level features that are built up from those basic features in the first layers.

The following topics will be covered in this chapter:

• Object detection
• CIFAR-10 object detection in mages—model building and training