There are two types of execution in Keras:
- Deferred (symbolic) execution
- Eager (imperative) execution
In deferred execution, we use Python to build a computation graph first, and then it's compiled so that it can be executed later. In eager execution, the Python runtime itself becomes the execution runtime for all the models.
In the next section, we will learn about deep learning using Keras. We will also look into visual recognition challenges, due to which deep learning became popular.