Welcome to Machine Learning
What Is Machine Learning?
You probably use machine learning many times a day without even knowing it. Every time you search for something on Google, Bing, or Baidu, machine learning software figures out how to rank the web pages so the most useful ones appear first.
When you upload a photo to Instagram or Snapchat and it automatically recognizes and tags your friends, that is machine learning. When a video streaming service recommends movies you might enjoy after you finish watching one, that is machine learning too.
Voice-to-text on your phone, asking Siri to play a song, or telling Google to show you nearby restaurants all rely on machine learning. Even your email service flagging a suspicious message titled “Congratulations! You have won a million dollars” as spam is an application of machine learning.
Machine Learning in Industry
Beyond consumer applications, AI is rapidly making its way into large companies and industrial settings:
- Energy: Machine learning is helping optimize wind turbine power generation, contributing to the fight against climate change.
- Healthcare: It is making its way into hospitals to help doctors make more accurate diagnoses.
- Manufacturing: Computer vision systems inspect items coming off the assembly line to detect defects.
Formal Definition
The most widely cited definition of machine learning is attributed to Arthur Samuel (1959). He defined machine learning as:
The field of study that gives computers the ability to learn without being explicitly programmed.
Samuel’s claim to fame was that back in the 1950s, he wrote a checkers-playing program. The remarkable thing was that Arthur Samuel himself was not a very good checkers player. What he did was have the computer play tens of thousands of games against itself. By observing which board positions tended to lead to wins and which tended to lead to losses, the program learned over time to recognize good and bad positions. By seeking out good positions and avoiding bad ones, the program got better and better at playing checkers.
Because the computer had the patience to play tens of thousands of games against itself, it accumulated so much experience that it eventually became a better checkers player than Samuel himself. This illustrates a key principle: the more opportunities you give a learning algorithm to learn, the better it will perform.
Review Questions
1. What would likely happen to the checkers program if it had played far fewer games against itself?
It would perform worse. The more data and experience a learning algorithm has, the better it performs. With fewer games, the program would have less information about which board positions lead to wins or losses, and would make poorer decisions.
1. Why is Arthur Samuel’s checkers program a good example of machine learning?
Samuel did not explicitly program the computer with checkers strategies. Instead, he gave it a framework to learn from its own experience (playing games against itself). The computer discovered winning patterns on its own, eventually surpassing its creator’s skill level.
Why Is Machine Learning So Widely Used?
Machine learning grew up as a sub-field of artificial intelligence (AI). The original goal was to build intelligent machines. It turns out there are a few basic things we can program a machine to do explicitly, such as finding the shortest path from point A to point B (like your GPS does). But for the most part, we simply did not know how to write an explicit program to do many of the more interesting things, such as:
- Perform web search
- Recognize human speech
- Diagnose diseases from X-rays
- Build a self-driving car
The only way we knew how to accomplish these tasks was to have a machine learn to do them by itself. That is what makes machine learning so powerful and so widely applicable.
Today, there are hundreds of thousands, perhaps millions of people working on machine learning applications across nearly every industry you can think of. It is hard to name an industry that machine learning is unlikely to touch in a significant way now or in the near future.
Artificial General Intelligence
Looking further into the future, many researchers are excited about the dream of someday building machines as intelligent as humans. This is sometimes called Artificial General Intelligence (AGI). However, AGI has been overhyped, and we are still a long way from that goal. It might take 50 years, 500 years, or longer to get there. Most AI researchers believe that the best way to get closer toward AGI is by using learning algorithms, possibly ones that take some inspiration from how the human brain works.
Economic Value of Machine Learning
According to a study by McKinsey, AI and machine learning is estimated to create an additional 13 trillion US dollars of value annually by the year 2030. Even though machine learning is already creating tremendous amounts of value in the software industry, there could be even vastly greater value yet to be created outside the software industry, in sectors such as retail, travel, transportation, automotive, materials, and manufacturing.
Because of these massive untapped opportunities across so many different sectors, there is a vast unfulfilled demand for machine learning skills today. That is what makes this such a great time to be learning about machine learning.
Types of Machine Learning
There are two main types of machine learning algorithms:
- Supervised learning learns from data that includes the “right answers” (labeled data). It is the type used most in real-world applications and has seen the most rapid advancement and innovation.
- Unsupervised learning finds patterns in data without labeled answers.
Beyond these two, other important types include recommender systems and reinforcement learning.
By far, the most used types of learning algorithms today are supervised learning, unsupervised learning, and recommender systems. In this specialization (three courses total), the first and second courses focus on supervised learning. The third course covers unsupervised learning, recommender systems, and reinforcement learning.
Review Questions
1. What are the two main types of machine learning?
Supervised learning and unsupervised learning.
1. Which type of machine learning is used most in real-world applications today?
Supervised learning. It is the most widely used and has seen the most rapid advancements and innovation.
Practical Skills Matter
Learning the algorithms alone is not enough. Having the tools is important, but knowing how to apply them effectively is equally (or even more) important. An analogy: giving someone a state-of-the-art hammer and drill does not mean they can build a house. They also need to know how to use those tools properly.
Even experienced machine learning teams at top tech companies sometimes spend six months going in the wrong direction because they do not know the best practices for applying these algorithms. In this course, you will learn not just the algorithms, but also the practical skills for developing valuable machine learning systems, so you are less likely to waste time on approaches that will not work.
What You Will Learn in This Course
In this course, you will learn about the most important machine learning algorithms, some of which are exactly what is being used at large tech companies today. Beyond the algorithms, you will also learn all the important practical tips and tricks for making them perform well. You will get to implement them and see how they work for yourself.
In the next section, we will look at a more formal definition of what machine learning is, and begin to talk about the main types of machine learning problems and algorithms.
Review Questions
1. Which of the following is NOT an example of machine learning mentioned in this lesson?
- A search engine ranking web pages
- A calculator performing arithmetic
- An email service filtering spam
- A streaming service recommending movies
b. A calculator performing arithmetic follows explicit programmed rules. Machine learning is about systems that learn from data without being explicitly programmed for every case.
1. In your own words, what does it mean that machine learning allows computers to “learn without being explicitly programmed”?
Instead of a programmer writing specific rules for every possible input (for example, a rule for every type of spam email), the system is given data and a learning algorithm that discovers the patterns by itself. The programmer provides the learning framework, not the specific answers.
1. Why did machine learning become necessary, according to this lesson?
For most interesting tasks (web search, speech recognition, medical diagnosis, self-driving cars), we simply did not know how to write explicit programs to solve them. The only way to accomplish these tasks was to have a machine learn to do them by itself from data.
1. What is Artificial General Intelligence (AGI), and why is it considered a distant goal?
AGI refers to building machines that are as intelligent as humans across all domains. It is considered distant because we are still far from achieving it, with estimates ranging from 50 to 500+ years. Most researchers believe learning algorithms are the best path toward it, but the goal itself remains uncertain and far off.
1. Name two industries outside of software where machine learning could create significant value.
Any two of: retail, travel, transportation, automotive, materials, or manufacturing.