Start course

This course introduces machine learning on Google Cloud Platform. 

Learning Objectives

  • What machine learning actually means
  • The types of problems machine learning can solve
  • The basics of how machine learning works

Intended Audience

  • Anyone interested in machine learning


  • A basic understanding of computers

I hope this course gave you a clearer picture of what machine learning is.  Now before I wrap things up, let me quickly recap everything that was covered.

First, you learned the differences between artificial intelligence, machine learning, and deep learning.  Remember, artificial intelligence is a wide field of study that is focused on creating machines with human-like intelligence.  Machine learning is a smaller subset of AI that focuses on creating machines that can “learn” or improve their own performance.   Deep learning is a specific subset of ML that involves building complex, multi-layered neural networks that basically emulate neurons in the human brain. 

Second, you learned about the different types of problems that machine learning is used to solve.  These break down into roughly four categories: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.  

Supervised learning requires a human supervisor to feed an algorithm a set of labeled data.  The supervisor also creates a bunch of tests to measure the accuracy of the algorithm.  Supervised learning is great for solving classification and regression problems.  

Unsupervised learning on the other hand does not require any labeled datasets or tests.  Instead, you directly feed in unlabeled data and the algorithm will identify categories on its own.  Unsupervised learning is great at solving clustering and association problems.

Semi-supervised learning combines elements from both supervised and unsupervised learning.  Basically, you provide a small labeled dataset for training.  But the rest of the data is unlabeled.

And reinforcement learning is basically trial-and-error.  The algorithm tries many different solutions and calculates their cost.  It then picks the solution with the most optimal cost.

Finally, we covered how machine learning actually works.  You feed data into an algorithm to create a model.  Then you can supply inputs (called features) and get back labels as outputs.  I also showed you a quick demo of training a machine-learning model and then using that model to make new predictions.

Well, that’s all I have for you today!  Remember to give this course a rating, and if you have any questions or comments, please let us know.  Thanks for watching, and make sure to check out our many other courses on Cloud Academy!

About the Author
Learning Paths

Daniel began his career as a Software Engineer, focusing mostly on web and mobile development. After twenty years of dealing with insufficient training and fragmented documentation, he decided to use his extensive experience to help the next generation of engineers.

Daniel has spent his most recent years designing and running technical classes for both Amazon and Microsoft. Today at Cloud Academy, he is working on building out an extensive Google Cloud training library.

When he isn’t working or tinkering in his home lab, Daniel enjoys BBQing, target shooting, and watching classic movies.