Python preparations

In the assignment for the first module we use Python to create and train deep neural networks. To get started, you should set up a working Python environment, following these instructions.

Some of you are already familiar with Python and for some this course will be their first experience with it. The preparations suggested below are optional but strongly recommended to those who have little experience with Python, or who wants to refresh their Python knowledge.

Python crash course

The Python crash course starts with Python basics and goes on to introduce Numpy and Matplotlib, two important Python modules (Python's name for packages or libraries).

Computer labs

The computer labs CL1 and CL2 specifically introduce you to Python for machine learning. The goal is to provide you with a few hands-on examples of simple regression and classification so that you can build intuition for these types of problems and to show you a standard way of developing a machine learning algorithm in Python. The labs will also introduce you to PyTorch. 

The labs come in the form of notebooks and can be downloaded here: computer-labs.zip Download computer-labs.zip .
Again, the computer labs are recommended, but not mandatory.

Individual home assignments

Two individual home assignments IHA1 and IHA2, allowing you to improve and test your coding skills by implementing ML models in Pytorch. The material for the home assignments can be found here: individual-home-assignments.zip Download individual-home-assignments.zip. The assignments are intended to be self-explanatory and they contain unit tests that should help you verify if your solutions are correct. There are some "grade" hints to help you choose what to focus on but note that the IHA's will not be graded and should not be submitted.