What this book covers

Chapter 1, The History of AI, begins by discussing the mathematical basis of AI and how certain theorems evolved. Then, we'll look at the research done in the 1980s and 90s to improve ANNs, we'll look at the AI winter, and we'll finish off with how we arrived at where we are today. 

Chapter 2, Machine Learning Basics, introduces the fundamentals of machine learning and AI. Here, we will cover essential probability theory, linear algebra, and other elements that will lay the groundwork for the future chapters.

Chapter 3, Platforms and Other Essentials, introduces the deep learning libraries of Keras and TensorFlow and moves onto an introduction of basic AWS terminology and concepts that are useful for deploying your networks in production. We'll also introduce CPUs and GPUs, as well as other forms of compute architecture that you should be familiar with when building deep learning solutions.

Chapter 4, Your First Artificial Neural Networks, explains how to build our first artificial neural network. Then, we will learn ability of the core elements of ANNs and construct a simple single layer network both in Keras and TensorFlow so that you understand how the two languages work. With this simple network, we will do a basic classification task, such as the MNIST OCR task.

Chapter 5, Convolutional Neural Networks, introduces the convolutional neural network and explains its inner workings. We'll touch upon the basic building blocks of convolutions, pooling layers, and other elements. Lastly, we'll construct a Convolutional Neural Network for image tagging.

Chapter 6, Recurrent Neural Networks, introduces one of the workhorses of deep learning and AI—the recurrent neural network. We'll first introduce the conceptual underpinnings of recurrent neural networks, with a specific focus on utilizing them for natural language processing tasks. We'll show how one can generate text utilizing you of these networks and see how they can be utilized for predictive financial models.

Chapter 7, Generative Models, covers generative models primarily through the lens of GANs, and we'll look at how we can accomplish each of the above tasks with GANs.

Chapter 8, Reinforcement Learning, introduces additional forms of neural networks. First, we'll take a look at autoencoders, which are unsupervised learning algorithms that help us recreate inputs when we don't have access to input data. Afterwards, we'll touch upon other forms of networks, such as the emerging geodesic neural networks.

Chapter 9, Deep Learning for Intelligent Assistant, focuses on utilizing our knowledge of various forms of neural networks from the previous section to make an intelligent assistant, along the lines of Amazon's Alexa or Apple's Siri. We'll learn about and utilize word embeddings, recurrent neural networks, and decoders.

Chapter 10, Deep Learning for Game Playing, explains how to construct game-playing algorithms with reinforcement learning. We'll look at several different forms of games, from simple Atari-style games to more advanced board games. We'll touch upon the methods that Google Brain utilized to build AlphaGo.

Chapter 11, Deep Learning for Finance, shows how to create an advanced market prediction system in TensorFlow utilizing RNNs.

Chapter 12, Deep Learning for Robotics, uses deep learning to teach a robot to move objects. We will first train the neural network in simulated environments and then move on to real mechanical parts with images acquired from a camera.

Chapter 13, Scale, Deploy and Maintain AI Application, introduces methods for creating and scaling training pipelines and deployment architectures for AI systems.