These lab tutorials are optional, but will help enhance your understanding of the topics covered in the lectures. It also aims to bridge the gap between the theory from the lectures and the practical implementation required for your coursework.
Each lab tutorial is presented as a Google Colab Notebook. This will allow you to run snippets of code interactively on a web interface.
To be able to save any changes you make to the notebook, please save a copy of the notebook to your own Google Drive, and run your own copy of the notebook on Google Colab. This is the easiest and recommended way to work on these tutorials.
Alternatively, you can download the notebook as an *.ipynb file and run it locally on your machine with Jupyter Notebook. A quick tutorial on Jupyter Notebook is available here on my Python Programming course.
If you have the notebook somewhere in your home directory on the departmental servers, and wish to run Jupyter Notebook/Lab remotely, search for “To use Jupyter Lab” on this page.
- Lab 1: Building a Machine Learning Pipeline
- Lab 2: K-Nearest Neighbours
- Lab 3: Machine Learning Evaluation
- Lab 4: Simple Linear Regression
- Lab 5: Multiple Linear & Logistic Regression, and PyTorch
- Lab 6: Unsupervised Learning
- Lab 7: Evolutionary Algorithms