Congratulations, you have now made it almost to the end of the course. Before you leave, we want to provide you with some additional tools that will be useful when you put your new skills into practice.

Start by reading chapter 11 in the course book. It will give you insights into how you practically define your machine learning problem (section 11.1), how to improve your model (section 11.2-11.3) and how to deal with common data issues such as missing values (section 11.4). In addition, section 11.5 in the book elaborates on interpretability and worst case guarantees of deep learning models.

Lastly, we will consider machine learning from an ethical perspective. To ensure safe deployment of machine learning models in society, we need to consider not only their advantages but also their limitations. You can read more about this in chapter 12 of the course book. Specifically, the course book elaborates on three machine learning-related ethical issues: fairness (chapter 12.1), misleading claims (chapter 12.2) and model bias resulting from biased or imbalanced data (chapter 12.3).

After you have read about practical and ethical issues of machine learning in the course book, you can move on to the last two examples. The first example is about predicting wine quality, and will include some of the practical aspects brought up in chapter 11 of the course book. In the second example, we will revisit the diabetes data and evaluate our model from a fairness perspective.

I've read chapters 11 and 12 in the course book.