Summary

In this chapter, we discussed AutoML, which aims to provide methods for model selection and hyperparameter optimization. AutoML is useful for beginners who have little expertise in making decisions such as how many layers to put in a model, which optimizer to use, and so on. AutoML is also useful for experts to both speed up the model training process and discover superior model architectures for a given task that would be nearly impossible to figure out manually.

In the next chapter, we will study another increasingly important and crucial aspect of machine learning, especially deep learning. We will closely look at how to interpret output produced by PyTorch models—a field popularly known as model interpretability or explainability.