Artificial Intelligence Fundamentals GOAA Practice Questions (Page 6)

Questions 26–30

1. 26foundation · easy

   Which statement best defines artificial intelligence (AI) in the context of computer science?

   • AA set of algorithms that can only execute predefined, rule-based instructions without any adaptation.
   • BA technology that guarantees perfect accuracy in decision-making without human intervention.
   • CThe study of how to build hardware that mimics the biological structure of the human brain.
   • DA branch of computer science focused on creating systems that perform tasks that typically require human intelligence.
   Reveal Solution Discussion Select an answer first
2. 27application · medium

   A data scientist is building a model to predict whether a loan applicant will default. They have historical data with features like income, credit score, and loan amount, and each record is labeled as 'default' or 'no default'. The model must output a probability of default. Which approach should they use?

   • ADeep learning without a training label
   • BSupervised classification with a probabilistic output
   • CReinforcement learning
   • DUnsupervised clustering
   Reveal Solution Discussion Select an answer first
4. 28foundation · easy

   How does deep learning differ from traditional machine learning?

   • ADeep learning is only used for image recognition, while traditional machine learning is used for all other tasks.
   • BDeep learning does not require data, while traditional machine learning does.
   • CDeep learning requires labeled data, while traditional machine learning does not.
   • DDeep learning uses neural networks with many layers, while traditional machine learning often uses simpler algorithms.
   Reveal Solution Discussion Select an answer first
5. 29application · easy

   A company wants to implement an AI system that can understand and respond to customer emails in natural language. They need the system to classify emails by intent (e.g., complaint, refund request) and draft appropriate replies. Which combination of AI subfields is most relevant?

   • AComputer vision and deep learning
   • BRobotics and reinforcement learning
   • CNatural language processing and machine learning
   • DExpert systems and rule-based reasoning
   Reveal Solution Discussion Select an answer first
6. 30expert · hard

   A security team is evaluating an AI-based intrusion detection system (IDS) that uses a deep neural network. The system has a very high detection rate on the test set, but in production it generates many false positives. The team suspects the model is overfitting. Which combination of factors is most likely contributing to this problem?

   • AThe model is underfitting because it has too few layers
   • BThe production traffic is too similar to the training data
   • CThe model is using unsupervised learning instead of supervised learning
   • DThe test set is not representative of production traffic, and the model has too many parameters
   Reveal Solution Discussion Select an answer first