Chapter 10: Training Deep Neural Networks on Azure
In the previous chapter, we learned how to train and score classical ML models using non-parametric tree-based ensemble methods. While these methods work well on many small- and medium-sized datasets that contain categorical variables, they don't generalize well on large datasets.
In this chapter, we will train complex parametric models using deep learning (DL) for even better generalization with very large datasets. This will help you understand deep neural networks (DNNs), how to train and use them, and when they perform better than traditional models.
First, we will provide a short and practical overview of why and when DL works well and focus on understanding the general principles and rationale rather than the theoretical approach. This will help you to assess which use cases and datasets need DL and how it works in general.
Then, we will look at one of the popular application domains for DL – computer vision...