Chapter 1, Introduction - Machine Learning and Statistical Science, covers various introductory concepts in machine learning. It talks about the history, branches and general discipline concepts. It also gives an introduction to the base mathematical concepts needed to understand most of the techniques developed afterward.
Chapter 2, The Learning Process, covers all the steps in the workflow of a machine learning process and shows useful tools and concept definitions for all those stages.
Chapter 3, Clustering, covers several techniques for unsupervised learning, specially K-Means, and K-NN clustering.
Chapter 4, Linear and Logistic Regression, covers two pretty different supervised learning algorithms, which go under a similar name: linear regression (which we will use to perform time series predictions), and logistic regression (which we will use for classification purposes).
Chapter 5, Neural Networks, covers one of the basic building blocks of modern machine learning Applications, and ends with the practical step-by-step building of a neural network.
Chapter 6, Convolutional Neural Networks, covers this powerful variation of neural networks, and ends with a practical tour of the internals of a very well known architecture of CNN, called VGG16, in a practical application.
Chapter 7, Recurrent Neural Networks, covers an overview of the RNN concept and a complete depiction of all the stages of the most used architecture, the LSTM. Finally, a practical exercise in time series prediction is shared.
Chapter 8, Recent Models and Developments, covers two upcoming techniques that have engaged huge interest in the field: generative adversarial networks, and the whole reinforcement learning field.
Chapter 9, Software Installation and Configuration, It covers the installation of all the necessary software packages, for three operative systems: Linux, macOS, and Windows.
