Chapter 4. Fundamentals of machine learning
This chapter covers
- Forms of machine learning beyond classification and regression
- Formal evaluation procedures for machine-learning models
- Preparing data for deep learning
- Feature engineering
- Tackling overfitting
- The universal workflow for approaching machine-learning problems
After the three practical examples in chapter 3, you should be starting to feel familiar with how to approach classification and regression problems using neural networks, and you’ve witnessed the central problem of machine learning: overfitting. This chapter will formalize some of your new intuition into a solid conceptual framework for attacking and solving deep-learning problems. We’ll consolidate all of these concepts—model evaluation, data preprocessing and feature engineering, and tackling overfitting—into a detailed seven-step workflow for tackling any machine-learning task.
In our previous examples, you’ve become familiar with three specific types of machine-learning problems: binary classification, multiclass classification, and scalar regression. All three are instances of supervised learning, where the goal is to learn the relationship between training inputs and training targets.
Supervised learning is just the tip of the iceberg—machine learning is a vast field with a complex subfield taxonomy. Machine-learning algorithms generally fall into four broad categories, described in the following sections.