Docsity
Log inSign up
Docsity
Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity

Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan

Guidelines and tips
Guidelines and tips
Sell on Docsity
Sell on Docsity
Log inSign up

Prepare for your exams

Study with the several resources on Docsity

Find documents

Prepare for your exams with the study notes shared by other students like you on Docsity

Search Store documents

The best documents sold by students who completed their studies

Search through all study resources
Docsity AINEW

Summarize your documents, ask them questions, convert them into quizzes and concept maps

Explore questions

Clear up your doubts by reading the answers to questions asked by your fellow students

Earn points to download

Earn points by helping other students or get them with a premium plan

Share documents
download point icon20 Points

For each uploaded document

Answer questions
download point icon5 Points

For each given answer (max 1 per day)

All the ways to get free points
Get points immediately

Choose a premium plan with all the points you need

Study Opportunities

Choose your next study program

Get in touch with the best universities in the world. Search through thousands of universities and official partners

Community

Ask the community

Ask the community for help and clear up your study doubts

University Rankings

Discover the best universities in your country according to Docsity users

Free resources

Our save-the-student-ebooks!

Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors

From our blog

Exams and Study
Go to the blog

ARTiBA Example Questions, Exams of Artificial Intelligence

California State University (CSU) - SacramentoArtificial Intelligence

Lot of example questions for the ARTiBA exam

Typology: Exams

2024/2025

Uploaded on 05/22/2025

unknown user
unknown user ๐Ÿ‡บ๐Ÿ‡ธ

1 / 11

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Fundamentals of AI & Machine Learning
1. What is the primary goal of Artificial Intelligence?
A. To mimic human emotions
B. To create machines that can think and act like humans
C. To replace human jobs entirely
D. To create faster computers
โœ… Correct Answer: B
2. Which of the following is NOT a type of machine learning?
A. Supervised Learning
B. Reinforcement Learning
C. Augmented Learning
D. Unsupervised Learning
โœ… Correct Answer: C
3. What is overfitting in machine learning?
A. When a model learns too much from training data and fails to generalize
B. When a model is too simple to capture patterns in data
C. When a model has a high bias and low variance
D. When a model does not learn from the training data
โœ… Correct Answer: A
4. Which algorithm is best suited for predicting continuous values?
A. Decision Trees
B. Logistic Regression
C. K-Means Clustering
D. Linear Regression
โœ… Correct Answer: D
5. Which of these techniques is used to reduce dimensionality in machine
learning?
A. PCA (Principal Component Analysis)
B. Gradient Boosting
C. K-Means Clustering
D. Naรฏve Bayes
โœ… Correct Answer: A
6. Which search algorithm is similar to Min-Max but removes unnecessary
branches?
A. Greedy search
B. Linear search
C. Alpha-beta pruning
D. Depth-first search
โœ… Correct Answer: C
pf3
pf4
pf5
pf8
pf9
pfa

Partial preview of the text

Download ARTiBA Example Questions and more Exams Artificial Intelligence in PDF only on Docsity!

Fundamentals of AI & Machine Learning

  1. What is the primary goal of Artificial Intelligence? A. To mimic human emotions B. To create machines that can think and act like humans C. To replace human jobs entirely D. To create faster computers โœ… Correct Answer: B
  2. Which of the following is NOT a type of machine learning? A. Supervised Learning B. Reinforcement Learning C. Augmented Learning D. Unsupervised Learning โœ… Correct Answer: C
  3. What is overfitting in machine learning? A. When a model learns too much from training data and fails to generalize B. When a model is too simple to capture patterns in data C. When a model has a high bias and low variance D. When a model does not learn from the training data โœ… Correct Answer: A
  4. Which algorithm is best suited for predicting continuous values? A. Decision Trees B. Logistic Regression C. K-Means Clustering D. Linear Regression โœ… Correct Answer: D
  5. Which of these techniques is used to reduce dimensionality in machine learning? A. PCA (Principal Component Analysis) B. Gradient Boosting C. K-Means Clustering D. Naรฏve Bayes โœ… Correct Answer: A
  6. Which search algorithm is similar to Min-Max but removes unnecessary branches? A. Greedy search B. Linear search C. Alpha-beta pruning D. Depth-first search โœ… Correct Answer: C
  1. Which of the following is an example of unsupervised learning? A. Predicting stock prices using historical data B. Identifying fraudulent transactions based on past fraud cases C. Grouping customers based on purchase behavior D. Classifying emails as spam or non-spam โœ… Correct Answer: C
  2. What is the main purpose of the loss function in a neural network? A. To determine the model's accuracy B. To update hyperparameters C. To measure the difference between predicted and actual values D. To normalize the data โœ… Correct Answer: C
  3. Which of the following is NOT a supervised learning algorithm? A. Support Vector Machines B. Decision Trees C. K-Means Clustering D. Random Forest โœ… Correct Answer: C
  4. Which AI technique is most commonly used for real-time decision-making? A. Reinforcement Learning B. Supervised Learning C. Clustering D. Linear Regression โœ… Correct Answer: A Neural Networks & Deep Learning
  5. What is the main advantage of Convolutional Neural Networks (CNNs)? A. They work best with tabular data B. They are good at processing sequential data C. They extract spatial features from images D. They require no training โœ… Correct Answer: C
  6. What does the pooling layer do in a CNN? A. Increases model complexity B. Reduces the dimensionality of feature maps
  1. Which AI method is used for detecting fraud? A. K-Means Clustering B. Anomaly Detection C. Reinforcement Learning D. Q-Learning โœ… Correct Answer: B
  2. Which AI technique powers Siri and Alexa? A. Reinforcement Learning B. Natural Language Processing (NLP) C. Generative Adversarial Networks (GANs) D. Support Vector Machines (SVMs) โœ… Correct Answer: B
  3. What is a common ethical concern with AI models? A. High accuracy B. Bias in training data C. Faster computation D. Lack of scalability โœ… Correct Answer: B Reinforcement Learning & Advanced AI Topics
  4. What is the key characteristic of Reinforcement Learning? A. Supervised learning with labeled data B. Learning from rewards and penalties C. Clustering similar data points D. Predicting continuous values โœ… Correct Answer: B
  5. Which algorithm is used in AI for playing strategic games? A. A* Search B. Min-Max Algorithm C. Logistic Regression D. K-Means Clustering โœ… Correct Answer: B
  6. Which generative AI model consists of a Generator and a Discriminator? A. GAN (Generative Adversarial Network) B. RNN C. CNN D. Decision Tree โœ… Correct Answer: A
  7. What is the main advantage of Transformer models? A. They work well with small datasets

B. They allow parallel processing for NLP tasks C. They are mainly used for image classification D. They reduce the need for GPUs โœ… Correct Answer: B

  1. Which AI concept is used to detect and track objects in videos? A. Object Detection B. Reinforcement Learning C. Feature Engineering D. Dimensionality Reduction โœ… Correct Answer: A AI Engineer (AIE)โ„ข Sample Questions
  2. AI Fundamentals Q1: What is the primary function of an activation function in a neural network? A) To reduce computational cost B) To introduce non-linearity into the model C) To normalize input data D) To optimize gradient descent โœ… Answer: B) To introduce non-linearity into the model Q2: Which AI technique is best suited for real-time object detection in images? A) K-Means Clustering B) Convolutional Neural Networks (CNNs) C) Principal Component Analysis (PCA) D) Linear Regression โœ… Answer: B) Convolutional Neural Networks (CNNs) Q3: What does the term "overfitting" mean in machine learning? A) The model performs well on training data but poorly on unseen data B) The model fails to learn from training data C) The model has too few parameters D) The model is too slow โœ… Answer: A) The model performs well on training data but poorly on unseen data Q4: Which algorithm is used for unsupervised learning? A) Logistic Regression
  1. AI Ethics & Governance Q9: What is a key challenge in AI fairness? A) High computational costs B) Bias in training data leading to discriminatory outcomes C) Slow model training D) Lack of open-source frameworks โœ… Answer: B) Bias in training data leading to discriminatory outcomes Q10: Which principle ensures AI systems are explainable? A) Scalability B) Interpretability C) Latency reduction D) Data augmentation โœ… Answer: B) Interpretability Q11: Which attention mechanism is used in the original Transformer architecture? A) Multi-head Self-Attention B) Global Average Pooling C) Bidirectional LSTM D) Radial Basis Function โœ… Answer: A) Multi-head Self-Attention (Key Concept: Transformers rely on self-attention to process sequential data in parallel.) Q12: In a CNN, what is the purpose of a "stride" in convolutional layers? A) To control the size of the kernel B) To skip pixels while sliding the filter, reducing output dimensions C) To add padding to the input D) To increase model depth โœ… Answer: B) To skip pixels while sliding the filter, reducing output dimensions (Example: A stride of 2 halves the spatial dimensions.) Q13: What does the "Q" stand for in Q-Learning? A) Quality B) Quantity C) Query D) Quick โœ… Answer: A) Quality (Explanation: Q-Learning learns a "quality function" for state-action pairs.) Q14: Which technique helps mitigate bias in a facial recognition dataset? A) Using only high-resolution images B) Ensuring balanced representation across demographics

C) Increasing model complexity D) Training on synthetic data only โœ… Answer: B) Ensuring balanced representation across demographics (Real-world Impact: Prevents skewed performance for certain groups.) Q15: What is the role of the "discriminator" in a GAN (Generative Adversarial Network)? A) Generates fake data samples B) Classifies real vs. fake data C) Optimizes the loss function for the generator D) Reduces noise in training data โœ… Answer: B) Classifies real vs. fake data (GANs pit generator vs. discriminator in a minimax game.) Machine Learning Engineer (MLE)โ„ข Sample Questions

  1. Supervised Learning Q1: Which evaluation metric is best for an imbalanced classification problem? A) Accuracy B) F1-Score C) Mean Squared Error (MSE) D) R-squared โœ… Answer: B) F1-Score Q2: What is the role of a validation set in model training? A) To test the final model B) To tune hyperparameters without overfitting C) To replace the test set D) To clean raw data โœ… Answer: B) To tune hyperparameters without overfitting Q3: Which algorithm is an example of ensemble learning? A) Linear Regression B) Random Forest C) K-Nearest Neighbors (KNN) D) Support Vector Machine (SVM) โœ… Answer: B) Random Forest
  2. Model Deployment & MLOps

C) Hyperparameter tuning D) Data labeling โœ… Answer: A) Distributed data processing Q10: Which technique helps prevent overfitting in decision trees? A) Increasing tree depth B) Pruning C) Adding more features D) Using a smaller dataset โœ… Answer: B) Pruning Q11: Which method is more efficient than grid search for hyperparameter optimization? A) Random Search B) Exhaustive Search C) Manual Tuning D) Fixed Defaults โœ… Answer: A) Random Search (Why? Random search explores the space more broadly with fewer trials.) Q12: What is the purpose of a "canary deployment" in ML systems? A) To roll out a model to a small subset of users before full release B) To train multiple models simultaneously C) To delete outdated models D) To encrypt model weights โœ… Answer: A) To roll out a model to a small subset of users before full release (Reduces risk by testing in production with limited exposure.) Q13: Which algorithm is specifically designed for time-series data with trends and seasonality? A) ARIMA (AutoRegressive Integrated Moving Average) B) K-Means C) DBSCAN D) Logistic Regression โœ… Answer: A) ARIMA (ARIMA handles non-stationary data via differencing and autoregression.) Q14: Which Google Cloud service is used for AutoML? A) Google BigQuery B) Vertex AI C) Cloud Spanner D) Dataflow

โœ… Answer: B) Vertex AI (Vertex AI provides AutoML tools for no-code/low-code model training.) Q15: What does SHAP (Shapley Additive Explanations) provide in ML? A) Feature importance values for model predictions B) A new loss function for training C) A data augmentation technique D) A clustering algorithm โœ… Answer: A) Feature importance values for model predictions (SHAP explains individual predictions using game theory.)