1

Machine Learning – an Introduction

Machine learning (ML) techniques are being applied in a variety of fields, and data scientists are being sought after in many different industries. With ML, we identify the processes through which we gain knowledge that is not readily apparent from data to make decisions. Applications of ML techniques may vary greatly and are found in disciplines as diverse as medicine, finance, and advertising.

In this chapter, we’ll present different ML approaches, techniques, and some of their applications to real-world problems, and we’ll also introduce one of the major open source packages available in Python for ML, PyTorch. This will lay the foundation for later chapters in which we’ll focus on a particular type of ML approach using neural networks (NNs). In particular, we will focus on deep learning (DL).
DL makes use of more advanced NNs than those used previously. This is not only a result of recent developments in the theory but also advancements in computer hardware. This chapter will summarize what ML is and what it can do, preparing you to better understand how DL differentiates itself from popular traditional ML techniques.

In this chapter, we’re going to cover the following main topics:

• Introduction to ML
• Different ML approaches
• Neural networks
• Introduction to PyTorch