Page 206 - AI Computer 10

E. Short answer type questions.

1. Differentiate between Artificial Intelligence, Machine Learning, and Deep Learning.
2. How does a learning-based AI model differ from a rule-based AI model?
3. Explain supervised learning with an example.
4. What is unsupervised learning, and how is it different from supervised learning?
5. Describe reinforcement learning in the context of a game-playing AI.

6. How do classification and regression models differ in their output?
7. What is the primary function of clustering models? Provide an example.
8. Explain the concept of association rule learning with an example.

9. How do Artificial Neural Networks (ANNs) mimic the human brain?
10. Describe a perceptron model to provide binary classification as output.
F. Long answer type questions.
1. What is Supervised, Unsupervised, and Reinforcement learning? Explain with an example of each.
2. What is clustering and how is it different from classification?

3. Differentiate between classification and regression model.
4. Explain the structure of an Artificial Neural Network (ANN) and describe how it processes input data.
5. Identify the type of learning (Supervised, Unsupervised, or Reinforcement) in the following case studies:

Case Study 1: A company wants to predict customer churn based on past purchasing behavior,
demographics, and customer interactions. They have a dataset with labeled examples of customers
who churned and those who did not.

Case Study 2: A social media platform wants to group users based on their interests and behavior to
recommend relevant content. They have a large dataset of user interactions but no predefined categories.
Case Study 3: An autonomous vehicle is learning to navigate through a city environment. It receives
feedback in the form of rewards for reaching its destination safely and penalties for traffic violations.
Case Study 4: A healthcare provider wants to identify patterns in patient data to personalize treatment
plans. They have a dataset with various patient attributes but no predefined labels indicating specific
treatment plans.
Case Study 5: A manufacturing company wants to optimize its production process by detecting anomalies
in sensor data from machinery. They have a dataset with examples of normal and anomalous behavior.
6. Evaluate the following scenarios to a perceptron model.
a. Context: Deciding Whether to Approve a Car for Rental

Factors:
• Car Condition: 1 if good, 0 if bad
• Driver Age: 1 if over 25, 0 if under 25

• Car Availability: 1 if available, 0 if not
• Driver Experience: 1 if experienced (5+ years), 0 if inexperienced
Weights and Bias:
• Weight for car condition = 2.0
• Weight for driver age = 1.5

72
72