AWS Certified Machine Learning – Specialty — Question 84

A health care company is planning to use neural networks to classify their X-ray images into normal and abnormal classes. The labeled data is divided into a training set of 1,000 images and a test set of 200 images. The initial training of a neural network model with 50 hidden layers yielded 99% accuracy on the training set, but only 55% accuracy on the test set.
What changes should the Specialist consider to solve this issue? (Choose three.)

Answer options

• A. Choose a higher number of layers
• B. Choose a lower number of layers
• C. Choose a smaller learning rate
• D. Enable dropout
• E. Include all the images from the test set in the training set
• F. Enable early stopping

Correct answer: B, D, F

Explanation

The correct answer includes choosing a lower number of layers (B), enabling dropout (D), and enabling early stopping (F). These changes help combat overfitting, which is likely causing the disparity between training and test accuracy. Increasing the number of layers (A) or including test images in training (E) would exacerbate the issue, while adjusting the learning rate (C) may not directly address overfitting.