2.1 Overview#

Keeping track of your code and experiments will be useful when you come to write up your work. You will be able to refer back to them to remind yourself of what you did and why you did it. This will make it easier for you to compare results and help you add details to your dissertation.

Hyperparameter tuning is also a key part of managing machine learning experiments. It will enable you to compare model performance under different settings and find the best model for your problem.

In this section, we will cover the following:

  • Git: understanding version control and how to use it

  • Hyperparameter Optimisation: how to find the best model for your problem

  • Logging: how to keep track of your experiments

Resources#