1 What is machine learning? It is common sense, except done by a computer

This chapter opens by demystifying machine learning as computers doing common-sense decision-making with data. It emphasizes that you don’t need heavy math or nonstop coding to get started—visual intuition, curiosity, and basic numeracy go a long way. The author highlights how ML now permeates everyday products and services thanks to abundant data and computing power, and sets an encouraging tone: the book will build understanding incrementally, using examples first and formulas/code as the “language” that clarifies them.

The text distinguishes artificial intelligence (computers making decisions) from machine learning (decisions from data), and then positions deep learning as a high-performing subset that uses neural networks. Using human reasoning as a guide, ML is framed as learning from experience—like recognizing apples by seeing many labeled examples—rather than hand-coding brittle rules. This shift from explicit instructions to pattern-finding in data is presented as a pivotal advance that enables computers to handle tasks too complex for traditional programming.

The core thinking process is the remember–formulate–predict framework: recall relevant data, distill it into a rule (a model), and use it to make predictions. The chapter defines models (rules that represent data) and algorithms (procedures that build models), and introduces features as the properties models rely on. A series of spam/ham examples shows how simple rules (frequency, weekday/weekend, message size) evolve into richer, multi-feature criteria, and how computers can efficiently search many candidate rules to find ones that fit data and generalize. Finally, it contrasts predictive ML (classification/regression) with generative ML (creating text or images), noting the book focuses on predictive methods while preparing readers for generative techniques later.

Machine learning is a part of artificial intelligence.

Machine learning encompasses all the tasks in which computers make decisions based on data. In the same way that humans make decisions based on previous experiences, computers can make decisions based on previous data.

Deep learning is a part of machine learning.

The remember-formulate-predict framework is the main framework we use in this book. It consists of three steps: (1) We remember previous data; (2) we formulate a general rule; and (3) we use that rule to make predictions about the future.

A very simple machine learning model

A slightly more complex machine learning model

Another slightly more complex machine learning model

An even more complex machine learning model

A much more complex machine learning model, found by a computer

Predictive machine learning is akin to answering questions, such as multiple choice. Generative learning is akin to writing an essay or drawing an image.

• Machine learning is easy! Anyone can learn it and use it, regardless of their background. All that is needed is a desire to learn and great ideas to implement!
• Machine learning is tremendously useful, and it is used in most disciplines. From science to technology to social problems and medicine, machine learning is making an impact and will continue doing so.
• Machine learning is common sense, done by a computer. It mimics the ways humans think to make decisions quickly and accurately.
• Just like humans make decisions based on experience, computers can make decisions based on previous data. This is what machine learning is all about.

• Remember: look at the previous data.
• Formulate: build a model, or a rule, based on this data.
• Predict: use the model to make predictions about future data.

FAQ