Cross-Validation

Resampling techniques are an important group of techniques in statistical data analysis. They involve repeatedly drawing samples from a dataset to create the training set and the test set. At each repetition, they fit and evaluate the model using the samples drawn from the dataset for the training set and the test set at that repetition. Using these techniques can provide us with information about the model that is otherwise not obtainable by fitting and evaluating the model only once using one training set and one test set. Since resampling methods involve fitting a model to the training data several times, they are computationally expensive. Therefore, when it comes to deep learning, we only implement them in the cases where the dataset and the network are relatively small and the available computational power allows us to do so.

In this section, you will learn about a very important resampling method called cross-validation. Cross-validation is one of the most important...