Courseiva

AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

What is the role of a label (also called target or ground truth) in supervised machine learning?

⚠ Common exam trap

Candidates often confuse the term 'label' in machine learning (ground truth output) with the general concept of a 'label' as a tag or category, leading candidates to mistakenly choose Option A or D.

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

The correct output or answer associated with each training example that the model learns to predict

In supervised machine learning, the label (also called target or ground truth) is the known correct output for each training example. The model uses these labels during training to learn the mapping from input features to outputs, enabling it to make accurate predictions on new, unseen data. This is fundamental to supervised learning, where the algorithm minimizes the error between its predictions and the ground truth labels.

Answer analysis

Option-by-option breakdown

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

  • A category of input features used by the model

    Why it's wrong here

    Input features are the independent variables or attributes that describe each training example, such as pixel intensities, sensor readings, or numeric encodings of categorical data. The model consumes these features as its known inputs, while labels are the unknown target outputs it must infer from them. Grouping features into categories helps with interpretation but does not define the answer the model is trained to produce.

  • The correct output or answer associated with each training example that the model learns to predict

    Why this is correct

    Labels are the ground-truth target values in a supervised learning dataset, representing the correct output the model should produce for each input example. During training, the model converts the input into a prediction, and the loss function measures how far that prediction is from the label, driving the weight updates. Labels can be discrete categories for classification or continuous numbers for regression.

  • A text description attached to a model explaining what it does

    Why it's wrong here

    Model descriptions are human-readable documentation, often stored in model cards or documentation files, that explain the intended use, limitations, and architecture of a model. They have no role in the training algorithm and do not provide a per-example expected output. In contrast, labels are structured data values inside the training set that the model explicitly learns to match.

  • A tag applied to Azure ML resources for organization

    Why it's wrong here

    Tags on Azure ML resources are key-value pairs used for resource organization, cost management, and permission scoping, such as marking an environment as dev or production. These tags are administrative metadata that lives outside the training dataset and never influence model weights. Labels, by contrast, are the ground-truth answer values embedded in each training sample that the model must learn to predict.

About these practice questions

One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.