MLS-C01 Question #215: Real Exam Question with Answer & Explanation

Question

A company wants to conduct targeted marketing to sell solar panels to homeowners. The company wants to use machine learning (ML) technologies to identify which houses already have solar panels. The company has collected 8,000 satellite images as training data and will use Amazon SageMaker Ground Truth to label the data. The company has a small internal team that is working on the project. The internal team has no ML expertise and no ML experience. Which solution will meet these requirements with the LEAST amount of effort from the internal team?

Options

• ASet up a private workforce that consists of the internal team. Use the private workforce and the
• BSet up a private workforce that consists of the internal team. Use the private workforce to label
• CSet up a private workforce that consists of the internal team. Use the private workforce and the
• DSet up a public workforce. Use the public workforce to label the data. Use the SageMaker Object

Explanation

To identify houses with solar panels from satellite images using Amazon SageMaker Ground Truth with the least effort from a small internal team lacking ML expertise, the company should set up a private workforce with the internal team and leverage Ground Truth's automated data labeling feature. This feature uses machine learning to pre-label data, reducing the manual labeling workload, and then use the SageMaker Object Detection algorithm for model training.

Common mistakes.

• B. Requiring the private internal workforce to manually label all 8,000 images would demand the maximum amount of effort from the team, directly contradicting the requirement for the "LEAST amount of effort."
• C. While custom labeling workflows offer flexibility, setting them up and managing them requires more expertise and effort than utilizing Ground Truth's built-in automated data labeling feature, especially for a team with no ML experience.
• D. Using a public workforce might reduce direct internal labeling effort but introduces other complexities like quality control and worker management, and it still lacks the efficiency benefit of the automated data labeling feature, which is the key to minimizing effort for the labeling task itself.

Concept tested. SageMaker Ground Truth automated data labeling

Reference. https://docs.aws.amazon.com/sagemaker/latest/dg/sms-automated-labeling.html

No community discussion yet for this question.