HML: Lesson - Three Ways for Machines to Learn

Three Ways for Machines to Learn

Think About It...

As we continue exploring machine learning, ask yourself a few questions:

Do you learn better when you have someone guiding you or teaching you directly?
Or do you prefer to do your own research?

Three Machine Learning Types

Three types of learning: supervised learning, unsupervised learning, reinforcement learning The key terms in the Overview lesson included three types of machine learning. We'll learn more about each one below, but for now, let's review the basic terms and their definitions:

Supervised Learning: a category of machine learning that uses labeled datasets to train algorithms to predict outcomes and recognize patterns.
Unsupervised Learning: a category of machine learning that uses uses machine learning algorithms to analyze and cluster unlabeled data sets. These algorithms discover hidden patterns or data groupings without the need for human intervention.
Reinforcement Learning: a category of machine learning that trains software to make decisions to achieve the most optimal results. It mimics the trial-and-error learning process that humans use to achieve their goals.

Each type of learning is covered in a video below. Be sure to watch each video, then complete the practice activity at the end of the page.

Video Lesson 1: Supervised Learning

Video Source: LearnFree (YouTube)

Video Lesson 2: Unsupervised Learning

Video Source: LearnFree (YouTube)

Video Lesson 3: Reinforcement Learning

Video Source: LearnFree (YouTube)

Practice Activity

[CC BY-NC-SA 4.0 Links to an external site.] UNLESS OTHERWISE NOTED | IMAGES: LICENSED AND USED ACCORDING TO TERMS OF SUBSCRIPTION - INTENDED ONLY FOR USE WITHIN LESSON.
inspiring.team/Shutterstock.com. Image used under license from Shutterstock.com and may not be repurposed.
Video source (all videos on page): All GCFGlobal.org® content is available for free at edu.gcfglobal.org.