Chapter 3. Machine learning


This chapter covers

  • Understanding why data scientists use machine learning
  • Identifying the most important Python libraries for machine learning
  • Discussing the process for model building
  • Using machine learning techniques
  • Gaining hands-on experience with machine learning

Do you know how computers learn to protect you from malicious persons? Computers filter out more than 60% of your emails and can learn to do an even better job at protecting you over time.

Can you explicitly teach a computer to recognize persons in a picture? It’s possible but impractical to encode all the possible ways to recognize a person, but you’ll soon see that the possibilities are nearly endless. To succeed, you’ll need to add a new skill to your toolkit, machine learning, which is the topic of this chapter.

3.1. What is machine learning and why should you care about it?

“Machine learning is a field of study that gives computers the ability to learn without being explicitly programmed.”

Arthur Samuel, 1959[1]

1Although the following paper is often cited as the source of this quote, it’s not present in a 1967 reprint of that paper. The authors were unable to verify or find the exact source of this quote. See Arthur L. Samuel, “Some Studies in Machine Learning Using the Game of Checkers,” IBM Journal of Research and Development 3, no. 3 (1959):210–229.

3.2. The modeling process

3.3. Types of machine learning

3.4. Semi-supervised learning

3.5. Summary