1 An overview of machine learning and deep learning

Deep learning has transformed computer vision, natural language and speech processing in particular, and artificial intelligence in general. From a bag of semi-discordant tricks, none of which worked satisfactorily on real-life problems, artificial intelligence has become a formidable tool to solve real problems faced by industry, at scale. This is nothing short of a revolution going on under our very noses. To lead the curve of this revolution, it is imperative to understand the underlying principles and abstractions rather than simply memorizing the “how-to” steps of some hands-on guide. This is where mathematics comes in.

In this first chapter, we present an overview of deep learning. This will require us to use some concepts explained in subsequent chapters. Don’t worry if there are some open questions at the end of this chapter: it is aimed at orienting your mind toward this difficult subject. As individual concepts become clearer in subsequent chapters, you should consider coming back and re-reading this chapter.

1.1 A first look at machine/deep learning: A paradigm shift in computation

1.2 A function approximation view of machine learning:Models and their training

1.3 A simple machine learning model: The cat brain

1.3.1 Input features

1.3.2 Output decisions

1.3.3 Model estimation

1.3.4 Model architecture selection

1.3.5 Model training

1.3.6 Inferencing

1.4 Geometrical view of machine learning

1.5 Regression vs. classification in machine learning

1.6 Linear vs. nonlinear models

1.7 Higher expressive power through multiple nonlinear layers: Deep neural networks

Summary