1
ARTIBA Artificial Intelligence Engineer
Exam 2025/2026 – Latest Verified
Questions with Correct Answers
AI and Machine Learning Concepts (20 Questions)
Question 1
What is the primary goal of artificial intelligence according to the AMDEX™ framework?
A) To replicate human consciousness
B) To enable machines to perform tasks requiring human intelligence
C) To create machines that experience emotions
D) To replace all human jobs
Answer: B) To enable machines to perform tasks requiring human intelligence
Rationale: The AMDEX™ framework defines AI as enabling machines to perform tasks
such as decision-making, pattern recognition, and problem-solving, which typically require
human intelligence.
Question 2
Which of the following is NOT a subfield of AI?
A) Machine Learning
B) Quantum Computing
C) Natural Language Processing
D) Computer Vision
Answer: B) Quantum Computing
Rationale: Quantum Computing is a field focused on computational advancements using
quantum mechanics, not a subfield of AI, unlike ML, NLP, and computer vision.
Question 3
What distinguishes supervised learning from unsupervised learning?
A) Supervised learning uses unlabeled data; unsupervised uses labeled data
B) Supervised learning maps inputs to known outputs; unsupervised finds patterns in unlabeled
data
C) Supervised learning clusters data; unsupervised predicts outputs
D) Both learn from labeled outputs
, 2
Answer: B) Supervised learning maps inputs to known outputs; unsupervised finds patterns
in unlabeled data
Rationale: Supervised learning uses labeled data to map inputs to outputs (e.g., regression,
classification), while unsupervised learning identifies patterns or structures in unlabeled data
(e.g., clustering).
Question 4
What does the bias-variance tradeoff refer to in machine learning?
A) Balancing underfitting and overfitting
B) Increasing model speed
C) Reducing training data size
D) Adjusting input variables
Answer: A) Balancing underfitting and overfitting
Rationale: The bias-variance tradeoff balances a model’s complexity to avoid underfitting
(high bias) and overfitting (high variance), ensuring good generalization to new data.
Question 5
What is overfitting in machine learning?
A) The model fails to capture relationships
B) The model performs better on test data
C) The model memorizes training data and performs poorly on new data
D) The model has no variance
Answer: C) The model memorizes training data and performs poorly on new data
Rationale: Overfitting occurs when a model learns noise and outliers in the training data,
reducing its ability to generalize to unseen data.
Question 6
How does regularization help prevent overfitting?
A) Increases model parameters
B) Removes features
C) Penalizes large weights in the loss function
D) Trains the model faster
Answer: C) Penalizes large weights in the loss function
Rationale: Regularization (e.g., L1, L2) adds a penalty term to the loss function,
discouraging overly complex models and improving generalization.
, 3
Question 7
What is the purpose of cross-validation in machine learning?
A) Reduces model size
B) Increases training data
C) Evaluates model performance on unseen data
D) Adjusts hyperparameters automatically
Answer: C) Evaluates model performance on unseen data
Rationale: Cross-validation (e.g., k-fold) splits data into training and validation sets to
assess a model’s performance on unseen data, ensuring robustness.
Question 8
Which AI agent operates based on a condition-action rule?
A) Goal-based agent
B) Simple reflex agent
C) Utility-based agent
D) Learning agent
Answer: B) Simple reflex agent
Rationale: A simple reflex agent uses condition-action rules to map specific conditions to
actions without maintaining internal state or planning.
Question 9
Which search algorithm is similar to minimax but removes branches that do not affect the final
output?
A) Greedy search
B) Linear search
C) Alpha-beta pruning
D) Depth-first search
Answer: C) Alpha-beta pruning
Rationale: Alpha-beta pruning enhances the minimax algorithm by eliminating branches
that cannot influence the final decision, improving efficiency in game-playing AI.
Question 10
ARTIBA Artificial Intelligence Engineer
Exam 2025/2026 – Latest Verified
Questions with Correct Answers
AI and Machine Learning Concepts (20 Questions)
Question 1
What is the primary goal of artificial intelligence according to the AMDEX™ framework?
A) To replicate human consciousness
B) To enable machines to perform tasks requiring human intelligence
C) To create machines that experience emotions
D) To replace all human jobs
Answer: B) To enable machines to perform tasks requiring human intelligence
Rationale: The AMDEX™ framework defines AI as enabling machines to perform tasks
such as decision-making, pattern recognition, and problem-solving, which typically require
human intelligence.
Question 2
Which of the following is NOT a subfield of AI?
A) Machine Learning
B) Quantum Computing
C) Natural Language Processing
D) Computer Vision
Answer: B) Quantum Computing
Rationale: Quantum Computing is a field focused on computational advancements using
quantum mechanics, not a subfield of AI, unlike ML, NLP, and computer vision.
Question 3
What distinguishes supervised learning from unsupervised learning?
A) Supervised learning uses unlabeled data; unsupervised uses labeled data
B) Supervised learning maps inputs to known outputs; unsupervised finds patterns in unlabeled
data
C) Supervised learning clusters data; unsupervised predicts outputs
D) Both learn from labeled outputs
, 2
Answer: B) Supervised learning maps inputs to known outputs; unsupervised finds patterns
in unlabeled data
Rationale: Supervised learning uses labeled data to map inputs to outputs (e.g., regression,
classification), while unsupervised learning identifies patterns or structures in unlabeled data
(e.g., clustering).
Question 4
What does the bias-variance tradeoff refer to in machine learning?
A) Balancing underfitting and overfitting
B) Increasing model speed
C) Reducing training data size
D) Adjusting input variables
Answer: A) Balancing underfitting and overfitting
Rationale: The bias-variance tradeoff balances a model’s complexity to avoid underfitting
(high bias) and overfitting (high variance), ensuring good generalization to new data.
Question 5
What is overfitting in machine learning?
A) The model fails to capture relationships
B) The model performs better on test data
C) The model memorizes training data and performs poorly on new data
D) The model has no variance
Answer: C) The model memorizes training data and performs poorly on new data
Rationale: Overfitting occurs when a model learns noise and outliers in the training data,
reducing its ability to generalize to unseen data.
Question 6
How does regularization help prevent overfitting?
A) Increases model parameters
B) Removes features
C) Penalizes large weights in the loss function
D) Trains the model faster
Answer: C) Penalizes large weights in the loss function
Rationale: Regularization (e.g., L1, L2) adds a penalty term to the loss function,
discouraging overly complex models and improving generalization.
, 3
Question 7
What is the purpose of cross-validation in machine learning?
A) Reduces model size
B) Increases training data
C) Evaluates model performance on unseen data
D) Adjusts hyperparameters automatically
Answer: C) Evaluates model performance on unseen data
Rationale: Cross-validation (e.g., k-fold) splits data into training and validation sets to
assess a model’s performance on unseen data, ensuring robustness.
Question 8
Which AI agent operates based on a condition-action rule?
A) Goal-based agent
B) Simple reflex agent
C) Utility-based agent
D) Learning agent
Answer: B) Simple reflex agent
Rationale: A simple reflex agent uses condition-action rules to map specific conditions to
actions without maintaining internal state or planning.
Question 9
Which search algorithm is similar to minimax but removes branches that do not affect the final
output?
A) Greedy search
B) Linear search
C) Alpha-beta pruning
D) Depth-first search
Answer: C) Alpha-beta pruning
Rationale: Alpha-beta pruning enhances the minimax algorithm by eliminating branches
that cannot influence the final decision, improving efficiency in game-playing AI.
Question 10
