Chapter 1, Getting Started with Supervised Learning, covers the big picture of AI and, in particular, deep learning. This chapter introduces the main machine learning concepts, from transforming data to evaluating results. These concepts will be useful in the following chapters, where we will focus only on deep learning applications.
Chapter 2, Neural Network Fundamentals, introduces the building blocks of deep learning and the math behind them. We will also explore concepts such as the perceptron and gradient descent, and the math behind them. We will then see how it's possible to use them to build neural networks with an example, to solve a classification task.
Chapter 3, Convolutional Neural Networks for Image Processing, covers more complex network architectures for solving domain-specific problems. In particular, we will look at some techniques for solving some computer vision problems. We will also see how a pre-trained network can reduce the time needed to create and train a neural network.
Chapter 4, Exploiting Text Embedding, shows how deep learning can be used for NLP tasks; in particular, how we can use embeddings to process textual data, the theory behind them, and some practical use cases.
Chapter 5, Working with RNNs, introduces a more sophisticated type of network, RNNs, and the math and the concepts behind them. In particular, we will focus on LSTM and how it can be used to solve an NLP problem.
Chapter 6, Reusing Neural Networks with Transfer Learning, introduces transfer learning, which is the ability of a model to generalize its learning to different tasks than the one it was trained to solve. We will also look at a concrete example of transfer learning using a pre-trained network to solve our particular problem using Keras and the famous VGG network.
Chapter 7, Working with Generative Algorithms, introduces one of the most innovative concepts in machine learning in the past decade: GANs. We will see how they work and the math behind them. We will also present an example of how to implement a GAN to generate simple handwritten digits.
Chapter 8, Implementing Autoencoders, talks about autoencoders, what they are, the math behind them, and which tasks they can solve. In particular, we will look at improvements to the simple autoencoders algorithm and how it's possible to use autoencoders to generate simple handwritten digits with Keras.
Chapter 9, Deep Belief Networks, talks about Deep Belief Networks (DBNs), what they are, the math behind them, and which tasks they can solve.
Chapter 10, Reinforcement Learning, introduces RL, starting from the basic concepts, such as the Monte Carlo and Markov chain methods. We will then explain traditional RL methods and how deep learning has improved and revitalized the field.
Chapter 11, What’s Next?, introduces a quick summary of all the topics that we have covered in the book. We will also provide readers with the details of other titles that could be used as reference materials. Lastly, we will also include the latest advancements that readers can look at in the field of neural networks.
