In this chapter we have learnt that following best practices will help on day to day activities as a Machine Learning engineer. We have seen how to prepare and split a dataset into subsets in order to facilitate proper training and fine tuning of a network. In addition we have looked at performing meaningful tests where the results achieved are representative of the ones that we will see when the model is deployed on the target application. Another topic that has been covered is overfitting and underfitting to data and what the best practices to follow are in order to address these issues. Furthermore, the problem of imbalanced datasets was addressed and we have seen a simple example of where this might be found (disease diagnosis). To solve this problem it was suggested to collect more data, augment the dataset and select evaluation metrics that are invariant to imbalanced datasets. Lastly, it was shown how to structure code in order to make it more readable and reusable.  

In the next chapter we will see how to manage large datasets and how to scale the training process to multiple GPUs and systems.