AI Practitioner · 20% of the exam

Fundamentals of AI and ML: free practice questions

5 sample questions from our 12-question bank for this domain — answers and explanations included. These are the same scenario-based style as the real AWS exam.

1. A model learns from a dataset where each example is labeled with the correct answer (e.g., emails labeled spam/not-spam). What type of machine learning is this?

  • A. Supervised learning✓ Correct
  • B. Unsupervised learning
  • C. Reinforcement learning
  • D. Generative pre-training only
Explanation

Learning from labeled examples is supervised learning. Unsupervised learning (B) finds structure in unlabeled data. Reinforcement learning (C) learns from rewards through interaction. Option D is not a learning paradigm in this taxonomy.

2. An e-commerce site must return a personalized product recommendation the instant a user loads a page, with sub-second latency. Which inference type is required?

  • A. Real-time (online) inference✓ Correct
  • B. Batch inference
  • C. Offline data labeling
  • D. Unsupervised clustering only
Explanation

Immediate, per-request, low-latency predictions require real-time (online) inference. Batch inference (B) processes accumulated data on a schedule — too slow for a live page load. Options C and D are not inference-serving modes for this scenario.

3. In a supervised dataset, which term refers to the OUTPUT the model is trained to predict?

  • A. The label (target)✓ Correct
  • B. The feature
  • C. The hyperparameter
  • D. The embedding
Explanation

The label (or target) is the known output the model learns to predict; features are the inputs. Hyperparameters (C) are training settings, and embeddings (D) are numeric vector representations of data — neither is the prediction target.

4. An algorithm groups customers into segments based on similarities in their behavior, with no predefined labels provided. Which learning type is this?

  • A. Unsupervised learning✓ Correct
  • B. Supervised learning
  • C. Reinforcement learning
  • D. Transfer learning
Explanation

Discovering groups or structure in unlabeled data is unsupervised learning (e.g., clustering). Supervised learning (B) requires labels. Reinforcement learning (C) uses rewards. Transfer learning (D) reuses a pretrained model for a new task — not a match for unlabeled segmentation.

5. Which example BEST represents UNSTRUCTURED data?

  • A. A collection of customer support call recordings and free-text emails✓ Correct
  • B. A relational table of orders with fixed columns
  • C. A CSV file with rows and typed columns
  • D. A database index
Explanation

Audio recordings and free-text emails have no fixed schema — that's unstructured data. A relational table (B) and a typed CSV (C) are structured. A database index (D) is a lookup structure, not a data-type classification.

7 more questions in this domain

Practice the full bank with instant grading, flashcards, and a timed mock exam.

Start practicing free