Designing and Implementing a Data Science Solution on Azure — Question 8

You are building a recurrent neural network to perform a binary classification.
You review the training loss, validation loss, training accuracy, and validation accuracy for each training epoch.
You need to analyze model performance.
You need to identify whether the classification model is overfitted.
Which of the following is correct?

Answer options

• A. The training loss stays constant and the validation loss stays on a constant value and close to the training loss value when training the model.
• B. The training loss decreases while the validation loss increases when training the model.
• C. The training loss stays constant and the validation loss decreases when training the model.
• D. The training loss increases while the validation loss decreases when training the model.

Correct answer: B

Explanation

The correct answer is B because overfitting occurs when the model performs well on the training data but poorly on unseen data, indicated by decreasing training loss and increasing validation loss. Options A, C, and D do not represent the typical behavior of a model that is overfitting, as they suggest different relationships between training and validation losses.