Python Programming

Aaaaaaaaaaand… end of the lesson!

Let’s recap!

In this lesson we covered:

• How Gradient Descent works and how it can be implemented.
• How to create and play with PyTorch tensors.
• How to perform automatic optimisation of parameters using PyTorch

We also provided a quick introduction to Deep Learning, and put into practice some of its concepts in two examples.

Are you able to answer all the questions below?

• Do you know how to implement Gradient Descent?
• Do you know how to automatically optimise some parameters to minimise a loss using PyTorch?
• How to create a PyTorch tensor?
• How to reshape and concatenate PyTorch tensors?
• How to implement a linear regression model?
• How to train a linear regression model?
• How to implement and train a classification model?
• How to implement and train an autoencoder?

That’s quite a lot covered in just a few chapters.

Don’t forget that all content of this lesson is non-examinable.

But hopefully, it will be useful for your incoming deep learning tutorials! ;)