Model Selection with Cross-Validation

Cross-validation provides us with robust estimation of model performance on unseen examples. For this reason, it can be used to decide between two models for a particular problem or to decide which model parameters (or hyperparameters) to use for a particular problem. In these cases, we would like to find out which model or which set of model parameters/hyperparameters results in the lowest test error rate. Therefore, we will select that model or that set of parameters/hyperparameters for our problem.

In this section, you are going to practice using cross-validation for this purpose. You will learn how to define a set of hyperparameters for your deep learning model and then write user-defined functions in order to perform cross-validation on your model for each of the possible combinations of hyperparameters. Then, you will observe which combination of hyperparameters leads to the lowest test error rate, and that combination will be your choice...