AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
A data scientist has a dataset containing thousands of labeled images of cats and dogs. The data scientist wants to train a model that can automatically classify new unlabeled images as either 'cat' or 'dog'. Which type of machine learning should the data scientist use?
⚠ Common exam trap
It's easy for candidates to confuse 'semi-supervised learning' with 'supervised learning' when they see a large labeled dataset, but semi-supervised learning is only appropriate when labeled data is scarce, not when thousands of labeled examples are already available.
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
✓
Supervised learning
Supervised learning, because the dataset contains labeled images (each image is tagged as 'cat' or 'dog'), and the goal is to train a model to predict the label for new unlabeled images. Supervised learning algorithms, such as convolutional neural networks (CNNs), learn a mapping from input features (pixel values) to output labels using the provided ground-truth labels, enabling accurate classification on unseen data.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Supervised learning
Why this is correct
Supervised learning is correct because the dataset consists of thousands of labeled images, meaning each input has a known ground-truth output. The model is trained on this input-output pairing to learn a mapping function, then applies it to predict labels for unseen images. This direct use of labeled examples to minimize prediction error is the defining characteristic of supervised learning, specifically classification when labels are categorical.
- ✗
Unsupervised learning
Why it's wrong here
Unsupervised learning is incorrect because it operates only on unlabeled data to discover hidden structures such as clusters, anomalies, or latent representations. Since the stem explicitly states that the dataset contains thousands of labeled images, each example already has a target label, eliminating the need for exploratory pattern finding. If labels were absent, methods like k-means or autoencoders would be appropriate, but here the availability of ground-truth labels makes supervised classification the correct paradigm.
When this WOULD be correct
A scenario where the dataset has no labels and the goal is to discover inherent groupings, such as clustering images of cats and dogs into two distinct clusters without any prior labeling.
- ✗
Reinforcement learning
Why it's wrong here
Reinforcement learning is incorrect because it involves an agent learning a policy through trial-and-error interactions with an environment, receiving scalar rewards or penalties based on its actions. There is no environment, no action space, and no reward signal in the scenario; instead, the available labeled images represent a static dataset, not a sequential decision-making task. Thus, the problem is not about maximizing cumulative reward but about generalizing from pre-existing examples.
When this WOULD be correct
A question where an agent must learn to play a game (e.g., chess or Atari) by interacting with an environment and receiving rewards for winning moves would require reinforcement learning.
- ✗
Semi-supervised learning
Why it's wrong here
Semi-supervised learning requires a small set of labelled data combined with a large pool of unlabelled data to infer structure, but the stem explicitly provides thousands of fully labelled images, removing the need to leverage unlabelled examples. It is tempting because semi-supervised methods can reduce labelling effort in real-world scenarios where labelled data is scarce, such as when only a few hundred labelled medical scans exist alongside many unlabelled ones.
When this WOULD be correct
A data scientist has a small set of labeled images of cats and dogs and a large set of unlabeled images. They want to improve classification accuracy by leveraging the unlabeled data alongside the labeled data.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓Supervised learningCorrect answer▾
Why this is correct
Supervised learning is correct because the dataset consists of thousands of labeled images, meaning each input has a known ground-truth output. The model is trained on this input-output pairing to learn a mapping function, then applies it to predict labels for unseen images. This direct use of labeled examples to minimize prediction error is the defining characteristic of supervised learning, specifically classification when labels are categorical.
✗Unsupervised learningWrong answer — click to see why▾
Why this is wrong here
The dataset contains labeled images, which provide ground truth for training. Unsupervised learning does not use labeled data, so it cannot be used for classification when labels are available.
★ When this WOULD be the correct answer
A scenario where the dataset has no labels and the goal is to discover inherent groupings, such as clustering images of cats and dogs into two distinct clusters without any prior labeling.
Why candidates choose this
Candidates may confuse unsupervised learning with the ability to handle unlabeled data during inference, but the key is that training data here is labeled.
✗Reinforcement learningWrong answer — click to see why▾
Why this is wrong here
Reinforcement learning is used for sequential decision-making with rewards/punishments, not for classifying static labeled images into predefined categories.
★ When this WOULD be the correct answer
A question where an agent must learn to play a game (e.g., chess or Atari) by interacting with an environment and receiving rewards for winning moves would require reinforcement learning.
Why candidates choose this
Candidates may confuse reinforcement learning with supervised learning because both involve feedback, but they overlook that reinforcement learning uses rewards rather than labeled examples.
✗Semi-supervised learningWrong answer — click to see why▾
Why this is wrong here
Semi-supervised learning is used when most data is unlabeled and only a small portion is labeled. Here, the dataset has thousands of labeled images, so supervised learning is appropriate.
★ When this WOULD be the correct answer
A data scientist has a small set of labeled images of cats and dogs and a large set of unlabeled images. They want to improve classification accuracy by leveraging the unlabeled data alongside the labeled data.
Why candidates choose this
Candidates may confuse semi-supervised learning with supervised learning, thinking that having some labeled data implies semi-supervised, but the key is the proportion of labeled vs. unlabeled data.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Supervised learning
Supervised learning is a type of machine learning where a model learns from labeled training data to make predictions or decisions.
Key term
Label
A label is a piece of metadata attached to data, objects, or resources to identify, classify, or describe them for easier management and retrieval.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
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.