AI Features
Home
Courses
Master AWS Certified AI Practitioner AIF-C01 Exam

Free AWS Certified AI Practitioner Exam Practice

The free AWS Certified AI Practitioner practice exam helps validate your understanding of AI/ML and generative AI fundamentals, including model life cycles, learning types, transformers, embeddings, and RAG techniques. It also covers model selection and evaluation, prompt engineering and fine-tuning, responsible and ethical AI practices, and securing and governing AI workloads on AWS.

We'll cover the following...

Question 1

A company wants to predict house prices based on size, location, and number of bedrooms. Which ML technique is the most appropriate?

A. Classification

B. Clustering

C. Regression

D. Reinforcement learning

Question 2

Which AWS service provides a fully managed environment to build, train, and deploy custom ML models?

A. Amazon Comprehend

B. Amazon SageMaker

C. Amazon Translate

D. Amazon Polly

Question 3

A logistics company aims to enhance delivery efficiency by predicting whether a shipment will arrive on time or late. The company has historical shipment data that includes delivery status, route distance, weather conditions, and carrier performance.

The business team insists that the model output must be interpretable so that delays can be explained to customers.

Which ML approach is most appropriate?

A. Regression model because delivery delay is time-based

B. Classification model because the outcome is categorical

C. Clustering model to group shipments with similar patterns

D. Reinforcement learning to optimize delivery routes dynamically

Question 4

Match each learning type with its correct description.

Match The Answer
Select an option from the left-hand side

A. Supervised learning

  1. Learns by receiving rewards or penalties

B. Unsupervised learning

  1. Uses labeled input-output pairs

C. Reinforcement learning

  1. Finds patterns in unlabeled data

Question 5

A health care organization trained a machine learning model to predict the risk of patient readmission. The model performs exceptionally well during training but shows significantly worse performance after deployment when new patient data is introduced.

Which ML life cycle concept addresses this issue most directly?

A. Hyperparameter tuning to improve model accuracy

B. Feature engineering to add more input variables

C. Model monitoring to detect data and concept drift

D. Exploratory data analysis (EDA) on historical data

E. Model retraining triggered by production feedback

...
Ask