In the previous chapters, we saw practical examples of how to build deep learning models to solve classification and regression problems, such as image classification and average user view predictions. Similarly, we developed an intuition on how to frame a deep learning problem. In this chapter, we will take a look at how we can attack different kinds of problems and different tweaks that we will potentially end up using to improve our model's performance on our problems.
In this chapter, we will explore:
- Other forms of problems beyond classification and regression
- Problems with evaluation, understanding overfitting, underfitting, and techniques to solve them
- Preparing data for deep learning
Remember, most ...
