Convolutional Neural Networks (CNNs or sometimes referred to as ConvNets) are fascinating. Over a short period of time, they became a disruptive technology, breaking all the state-of-the-art results in multiple domains from text, to video, to speech--going well beyond their original use for image processing. In this chapter, we will present a number of recipes as follows:
- Creating a ConvNet to classify handwritten MNIST numbers
- Creating a ConvNet to classify CIFAR-10
- Transferring style with VGG19 for image repainting
- Using a pretrained VGG16 net for transfer learning
- Creating a DeepDream network
