Google Cloud Professional Machine Learning Engineer — Question 3

You have trained a deep neural network model on Google Cloud. The model has low loss on the training data, but is performing worse on the validation data. You want the model to be resilient to overfitting. Which strategy should you use when retraining the model?

Answer options

• A. Apply a dropout parameter of 0.2, and decrease the learning rate by a factor of 10.
• B. Apply a L2 regularization parameter of 0.4, and decrease the learning rate by a factor of 10.
• C. Run a hyperparameter tuning job on AI Platform to optimize for the L2 regularization and dropout parameters.
• D. Run a hyperparameter tuning job on AI Platform to optimize for the learning rate, and increase the number of neurons by a factor of 2.

Correct answer: C

Explanation

The correct answer is C because running a hyperparameter tuning job allows you to systematically explore various configurations of both L2 regularization and dropout, which are essential in combating overfitting. Options A and B involve specific changes that may not be optimal, while option D focuses on the learning rate and increasing neurons, which does not directly address the overfitting issue.