Start course
1h 1m

This course introduces you to PyTorch and focuses on two main concepts: PyTorch tensors and the autograd module. We are going to get our hands dirty throughout the course, using a demo environment to explore the methodologies covered. We’ll look at the pros and cons of each method, and when they should be used.

Learning Objectives

  • Create a tensor in PyTorch
  • Understand when to use the autograd attribute
  • Create a dataset in PyTorch
  • Understand what backpropagation is and why it is important

Intended Audience

This course is intended for anyone interested in machine learning, and especially for data scientists and data engineers.


To follow along with this course, you should have PyTorch version 1.5 or later.


The Python scripts used in this course can be found in the GitHub repo here: 



Congratulations! You have reached the end of the course. I hope you enjoyed it as much as I did. PyTorch is a really cool ecosystem that is getting more and more popular, so it is worth spending time learning it if you wish to have a career in data science.

So today we have learnt a few things. First, we learnt what PyTorch is and its fundamental building blocks, namely tensors and the autograd module.

In particular, we saw how to create a tensor, and how to perform operations between tensors. We also looked at how to create a dataset in PyTorch, and how to load a custom dataset inPyTorch. We also saw how to use the autograd module, which is a very important package in PyTorch, and this is used to compute gradients. Finally we explored the concept of backpropagation and we wrapped up all the concepts we saw when dealing with the autograd module through an example with an OLS model.

That now brings me to the end of this course. We love your feedback, so please contact our support team for any thoughts, comments, or suggestions about this content, and thanks for learning with Cloud Academy.

About the Author
Learning Paths

Andrea is a Data Scientist at Cloud Academy. He is passionate about statistical modeling and machine learning algorithms, especially for solving business tasks.

He holds a PhD in Statistics, and he has published in several peer-reviewed academic journals. He is also the author of the book Applied Machine Learning with Python.