AWS Certified Machine Learning – Specialty — Question 12
A Machine Learning Specialist has created a deep learning neural network model that performs well on the training data but performs poorly on the test data.
Which of the following methods should the Specialist consider using to correct this? (Choose three.)
Answer options
- A. Decrease regularization.
- B. Increase regularization.
- C. Increase dropout.
- D. Decrease dropout.
- E. Increase feature combinations.
- F. Decrease feature combinations.
Correct answer: B, C, F
Explanation
The correct answers are B, C, and F. Increasing regularization (B) and dropout (C) helps to prevent overfitting, which is why the model is performing poorly on the test data. Decreasing feature combinations (F) can also help by reducing the model's complexity. The other options would likely exacerbate the overfitting issue.