AWS Certified Machine Learning – Specialty — Question 20

A Machine Learning Specialist is required to build a supervised image-recognition model to identify a cat. The ML Specialist performs some tests and records the following results for a neural network-based image classifier:
Total number of images available = 1,000
Test set images = 100 (constant test set)
The ML Specialist notices that, in over 75% of the misclassified images, the cats were held upside down by their owners.
Which techniques can be used by the ML Specialist to improve this specific test error?

Answer options

• A. Increase the training data by adding variation in rotation for training images.
• B. Increase the number of epochs for model training
• C. Increase the number of layers for the neural network.
• D. Increase the dropout rate for the second-to-last layer.

Correct answer: A

Explanation

The correct answer is A because increasing the training data with images showing cats in various orientations, including upside down, will help the model learn to recognize cats in those positions. The other options may improve general performance but won't specifically address the issue of misclassifying upside-down cats.