MLS-C01 Modeling Practice Question

A data scientist is training a deep learning model using Amazon SageMaker. The training loss is decreasing, but the validation loss starts increasing after 10 epochs. The model is overfitting. Which TWO actions should the data scientist take to reduce overfitting? (Choose 2.)

⚠ Common exam trap

It's easy for candidates to confuse regularization techniques that reduce overfitting (dropout, L2, early stopping) with actions that increase model capacity (more layers, more steps), leading them to select options that would worsen the problem.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Add dropout layers

Dropout layers randomly deactivate a fraction of neurons during training, which forces the network to learn more robust features and reduces co-adaptation, a common cause of overfitting. This technique is particularly effective in deep learning models trained on SageMaker, where large architectures can quickly memorize training data.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Increase the number of layers
Why it's wrong here
Increases model capacity, worsens overfitting.
✗
Remove L2 regularization
Why it's wrong here
Regularization helps reduce overfitting.
✗
Increase the number of training steps
Why it's wrong here
More steps can lead to more overfitting.
✓
Add dropout layers
Why this is correct
Dropout regularizes by randomly dropping neurons.
✓
Add early stopping based on validation loss
Why this is correct
Stops training when validation loss stops improving.

Go deeper

MLS-C01 Modeling Practice Question

Why each option matters

Option-by-option breakdown

Related to this question