3 Types of Machine Learning You Should Know

Machine learning (ML) is a specialized technology that falls under the umbrella of artificial intelligence (AI). This exciting field is the driving power behind many modern technologies, including image recognition, self-driving cars, and products like Amazon's Alexa.

The global ML market is predicted to grow to more than $188 billion by 2029, up from $21 billion in 2022, according to Fortune Business Insights [1]. Rapid growth in the field of machine learning means there is plenty of opportunity to dive into a related career.

When you decide to start the journey into machine learning, there are three main types of machine learning you should know. Below, we cover each of these different approaches in depthe. If you'd like to learn even more about machine learning from industry experts, you might consider enrolling in Stanford and DeepLearning.AI's Machine Learning Specialization.

What is machine learning?

This field of study uses data and algorithms to mimic human learning, allowing machines to improve over time, becoming increasingly accurate when making predictions or classifications or uncovering data-driven insights. It works in three basic ways, starting with using a combination of data and algorithms to predict patterns and classify data sets, an error function that helps evaluate the accuracy, and then an optimization process to fit the data points into the model best.

Did you know?

Arthur Samuel created the term "machine learning" in reference to his research in the early 1960s. That research was based on the checkers game that Robert Nealy played against an IBM 7094 computer and lost. Although this is minor compared to what machines can do today, it was a groundbreaking milestone at the time.

Applications of machine learning 

Machine learning is already used around us and you may not realize how it impacts your life. Here's a few ways it's used that you should know:

• Social media features: Social media platforms integrate machine learning algorithms to help deliver personalized experiences to you. Facebook notes your activities, including your comments, likes, and the time you spend on different types of content. The algorithm learns from your activity and makes pages and friend suggestions tailored to you.

• Virtual assistants: Apple's Siri, Amazon's Alexa, and Google Now are all popular options if you're looking for a virtual personal assistant. These voice-activated devices can do everything from search for flights to check your schedule to set alarms and more. Machine learning is a key component of these smart devices and speakers. They collect information and refine it each time you interact with them. The machine can then use that data to give you results that are best matched to your preferences.

• Recommendation engines: Popular among e-commerce websites, product recommendations are a common machine learning application. It lets these sites track your behavior based on input variables such as your searches, previous purchases, and your shopping cart history to make suggestions and recommendations about products you may be interested in.

• Image recognition: This complex technology is cropping up in a variety of fields. You've probably encountered this in your everyday life while uploading a photo to your social media platform. When you tag someone in an image, the platform recognizes them. It can also be transformative for identifying potential threats or criminals, unlocking phones and mobile devices, and finding missing persons.

Hear more about the real-world applications of machine learning in this lecture from Stanford and DeepLearning.AI's Machine Learning Specialization:

3 types of machine learning  

Machine learning involves showing a large volume of data to a machine so that it can learn and make predictions, find patterns, or classify data. The three machine learning types are supervised, unsupervised, and reinforcement learning.

1. Supervised learning

Gartner, a business consulting firm, predicts supervised learning will remain the most utilized machine learning among enterprise information technology leaders through 2022 [2]. This type of machine learning feeds historical input and output data in machine learning algorithms, with processing in between each input/output pair that allows the algorithm to shift the model to create outputs as closely aligned with the desired result as possible. Common algorithms used during supervised learning include neural networks, decision trees, linear regression, and support vector machines.

This machine learning type got its name because the machine is “supervised” while it's learning, meaning you’re feeding the algorithm information to help it learn. The outcome you provide the machine is labeled data, and the rest of the information you give is used as input features. 

For example, if you were trying to learn about the relationships between loan defaults and borrower information, you might provide the machine with 500 cases of customers who defaulted on their loans and another 500 who didn't. The labeled data “supervises” the machine to figure out the information you're looking for.

Supervised learning examples

Supervised learning is effective for a variety of business purposes, including sales forecasting, inventory optimization, and fraud detection. Some examples of use cases include:

• Predicting real estate prices

• Classifying whether bank transactions are fraudulent or not

• Finding disease risk factors

• Determining whether loan applicants are low-risk or high-risk

• Predicting the failure of industrial equipment's mechanical parts

2. Unsupervised learning

While supervised learning requires users to help the machine learn, unsupervised learning algorithms don't use the same labeled training sets and data. Instead, the machine looks for less obvious patterns in the data. Unsupervised machine learning is very helpful when you need to identify patterns and use data to make decisions. Common algorithms used in unsupervised learning include Hidden Markov models, k-means, hierarchical clustering, and Gaussian mixture models.

Using the example from supervised learning, let's say you didn't know which customers did or didn't default on loans. Instead, you'd provide the machine with borrower information, and it would look for patterns between borrowers before grouping them into several clusters.

Unsupervised learning examples

Unsupervised algorithms are widely used to create predictive models. Common applications also include clustering, which creates a model that groups objects together based on specific properties, and association, which identifies the rules between the clusters. A few example use cases include:

• Creating customer groups based on purchase behavior

• Grouping inventory according to sales and/or manufacturing metrics

• Pinpointing associations in customer data (for example, customers who buy a specific style of handbag might be interested in a specific style of shoe)

What is semi-supervised learning?

Semi-supervised learning has characteristics from both supervised and unsupervised learning. It may be used to avoid the costly labeling process or when there is insufficient labeled data for a supervised learning algorithm.

3. Reinforcement learning

Reinforcement learning is the closest machine learning type to how humans learn. The algorithm or agent used learns by interacting with its environment and getting a positive or negative reward. Common algorithms include temporal difference, deep adversarial networks, and Q-learning.

Going back to the bank loan customer example, you might use a reinforcement learning algorithm to look at customer information. If the algorithm classifies them as high-risk and they default, the algorithm gets a positive reward. If they don't default, the algorithm gets a negative reward. In the end, both instances help the machine learn by understanding both the problem and environment better.

Gartner notes that most ML platforms don't have reinforcement learning capabilities because they require higher computing power than most organizations have [2]. Reinforcement learning is applicable in areas capable of being fully simulated that are either stationary or have large volumes of relevant data. Because this type of machine learning requires less management than supervised learning, it’s viewed as easier to work with when dealing with unlabeled data sets.

Reinforcement learning examples

Practical applications for this type of machine learning are still emerging. Some examples of uses include:

• Teaching cars to park themselves and drive autonomously

• Dynamically controlling traffic lights to reduce traffic jams

• Training robots to learn policies using raw video images as input that they can use to replicate the actions they see

Learn more about reinforcement learning in this lecture from the University of Alberta's Fundamentals of Reinforcement Learning course:

Career paths in machine learning 

The World Economic Forum's “Future of Jobs Report 2023” names AI and Machine Learning Specialists among the top fastest-growing jobs [3]. In 2023, Indeed ranked machine learning engineer number eight on its list of the Best Jobs in the United States [4]. Machine learning is an in-demand field that lends itself to several possible career paths, including:

*All salary data sourced from Glassdoor as of March 2024.

Machine learning engineer: In this role, you can work on machine learning projects and create and manage platforms. 

• Average annual salary (US): $127,712

Data scientist: In this role, you can use a combination of machine learning and predictive analytics to collect, analyze, and interpret data. 

• Average annual salary (US): $120,508

Natural language processing (NLP) engineer: In this role, you can work with computers, computer science, and computational language to form connections between the way humans communicate and computers understand and interpret human language. 

• Average annual salary (US): $87,248

Business intelligence developer: In this role, you’ll focus on analyzing data to gather insight into business and market trends. 

• Average annual salary (US): $114,375

How to get started in machine learning

Most employers look for a combination of education and experience. Here are three common ways to set yourself on the path to the job you want: 

1. Earn a degree.

Start your career path with a bachelor's degree in data science, computer programming, computer science, or a related field. Machine learning is an advanced field and employers tend to hire candidates with a bachelor's degree. However, with adequate work experience and alternative credentials, those with associate degrees or high school diplomas can also get started in machine learning.

2. Gain work experience.

Try to land an internship or entry-level position in machine learning-related roles in software development, software engineering, data engineering, or data science. You can also gain experience through online courses, certification programs, and hands-on projects. Here are a few recommendations to get you started:

• Build a Machine Learning Web App with Streamlit and Python (Guided Project)

• Unsupervised Machine Learning for Customer Market Segmentation (Guided Project)

• Cervical Cancer Risk Prediction Using Machine Learning (Guided Project)

• Machine Learning Specialization by Stanford University and DeepLearning.AI

• IBM Machine Learning Professional Certificate

3. Advance your career.

Consider earning a master's degree or brushing up on your skills with a professional certificate. Many employers prefer to hire machine learning professionals with advanced degrees in software engineering, computer science, machine learning, or AI.

Start building ML expertise today with Coursera

Learn the fundamentals of machine learning and develop the skills needed to build and train deep neural networks with the Deep Learning Specialization from DeepLearning.AI. If you’re on your way to a career in machine learning, explore how a data science degree could unlock new opportunities.