Questions AI – Unit 1 and Unit 2

UNIT 1 ANSWERS
Objective MCQs
1. What is the purpose of defining the problem statement during the Problem Scoping stage in
an AI project cycle?
B) To understand the aim and objective of the project
A well-defined problem statement provides focus, aligns the team, and sets measurable goals for the
project1.
2. In what ways can AI models be categorized based on the type of data fed into them?
C) Three domains
AI models are commonly categorized as supervised, unsupervised, and reinforcement learning, based
on the type of data2.
3. In Statistical Data, what is the primary function of the system in relation to data?
B) Analyzing data to extract insights
Statistics is fundamentally about analyzing, interpreting, and summarizing data to make informed
decisions3.
4. What is the main goal of Computer Vision projects?
D) Converting digital visual data into computer-readable language
Computer vision enables machines to interpret and understand the visual world by converting images
into meaningful data4.
5. What is the primary focus of NLP?
C) Dealing with the interaction between computers and humans using natural language
NLP is AI focused on the interaction between computers and humans using natural language5.
6. What do frameworks provide in the context of problem-solving?
B) Step-by-step guidance
Frameworks guide the process of defining, analyzing, and solving problems systematically6.
7. How are Ethical Frameworks for AI categorized?
B) Into sector-based and value-based frameworks
Ethical frameworks are often divided into sector-based (industry-specific) and value-based (principle-
driven) categories.
8. What is the central focus of virtue-based value-based frameworks?
C) Aligning actions with ethical principles and beliefs
Virtue-based frameworks focus on the character and ethical principles guiding actions.
9. Which of the following best describes rights-based value-based frameworks?
A) Prioritizing human rights and dignity, valuing human life over other considerations
Rights-based frameworks emphasize human rights and dignity above all.
10. What is the primary domain of application for Bioethics?
B) Healthcare and life sciences
Bioethics deals with ethical issues in healthcare and life sciences.
11. Assertion: Ethics provide guidance in distinguishing right from wrong.
Reasoning: Ethics consist of a set of values and morals that aid individuals in making moral
judgments and decisions.
 A) Both Assertion and Reasoning are true, and Reasoning is the correct explanation of the
Assertion.
12. Assertion: Value-based frameworks in ethics provide guidance by focusing on fundamental
ethical principles and values.
Reasoning: These frameworks reflect different moral philosophies guiding ethical reasoning
and are concerned with assessing the moral worth of actions.
A) Both Assertion and Reasoning are true, and Reasoning is the correct explanation of the
Assertion.
Reflection Time
1. Outline the main steps in the AI Project Cycle briefly.
• Problem Scoping (defining the problem)
• Data Acquisition
• Data Exploration
• Modelling
• Evaluation
• Deployment
2. What roles does computer vision play in agricultural monitoring systems?
• Crop health monitoring
• Pest/disease detection
• Yield estimation
• Automated irrigation control
3. Mention the factors which knowingly or unknowingly influence our decision-making.
• Personal biases
• Social influences
• Emotions
• Past experiences
• Cultural background
4. What is the necessity for Ethical Frameworks in AI development?
• To ensure AI systems are fair, transparent, accountable, and respect human rights and societal values.
5. Mention the key characteristics of sector-based frameworks.
• Tailored to specific industries (e.g., healthcare, finance)
• Address sector-specific risks and regulations
• Provide practical guidelines for implementation
6. What do you mean by Bioethics?
• Bioethics is the study of ethical issues arising from advances in biology and medicine, focusing on
patient rights, consent, and the implications of medical technologies.
7. What is Natural Language Processing? Explain any two real-life applications of NLP.
• NLP is a branch of AI that enables computers to understand, interpret, and interact using human
language.
• Application 1: Chatbots for customer service
• Application 2: Sentiment analysis for social media monitoring
8. How do value-based frameworks contribute to ethical decision-making by emphasizing
fundamental principles and values?
• They guide actions by focusing on core ethical principles (e.g., justice, rights, virtues), ensuring
decisions align with societal and moral values.
UNIT 2 ANSWERS
Q1. Difference between rule-based and learning-based AI models
Rule-Based AI Models Learning-Based AI Models
Use explicitly coded rules (if-then-else) by humans to Learn patterns and relationships from data without explicit
make decisions12. rules from humans12.
Rigid, limited to the knowledge base programmed by
Adaptive; can improve and change with new data2.
developers2.
Do not learn from new data; static intelligence2. Can generalize and handle new, unseen situations2.
Example: Expert systems, chatbots with fixed
Example: Neural networks, machine learning models.
responses.

Q2. What is supervised, unsupervised, and reinforcement learning?

Explain with examples.
• Supervised Learning:
Uses labeled data (input-output pairs) to train models to predict outputs for new data3.
Example: Email spam detection, where emails are labeled as "spam" or "not spam"3.
• Unsupervised Learning:
Uses unlabeled data to find patterns or groupings within the data4.
Example: Customer segmentation in marketing, where groups are formed based on purchasing behavior4.
• Reinforcement Learning:
An agent learns to make decisions by receiving rewards or punishments for its actions5.
Example: Training a robot to navigate a maze by rewarding it for reaching the exit and penalizing for hitting
walls5.

Q3. What is clustering and how is it different from classification?

• Clustering:
An unsupervised learning technique that groups similar data points together based on features, without pre-
defined labels67.
Example: Grouping customers by purchasing habits.
• Difference from Classification:
o Classification is supervised and assigns pre-defined labels to data based on training with labeled
examples7.
o Clustering is unsupervised and finds natural groupings in data without labels7.

Q4. Explain neural networks. Also give functions of three layers of neural
networks.
 • Neural Network:
A machine learning model inspired by the human brain, consisting of interconnected nodes (neurons)
organized in layers8.
It learns to recognize patterns and make decisions through training on data8.
• Three Layers:
o Input Layer: Receives raw data/features and passes them to the next layer8.
o Hidden Layer(s): Performs computations, extracts features, and identifies patterns8.
o Output Layer: Produces the final prediction or classification8.

Q5. Differentiate between classification and regression model.

Classification Regression
Predicts discrete categories/labels7. Predicts continuous numerical values.
Example: Spam or not spam. Example: Predicting house prices.
Output is class/category. Output is a real number.

Q6. What is neural network? Give the functioning of its three layers.
• Neural Network: See Q4 above8.
• Functioning of three layers: See Q4 above8.

Q7. Identify the type of learning for each case study.

a) Supervised Learning

• Labeled data (churn/no churn) is used to predict customer churn3.

b) Unsupervised Learning

• No predefined categories; users are grouped based on behavior (clustering)46.

c) Reinforcement Learning

• Agent (vehicle) learns via rewards/penalties for actions5.

d) Unsupervised Learning

• No labels, patterns are identified in patient data (clustering)46.

e) Supervised Learning

• Labeled data (normal/anomaly) is used to detect anomalies3.

Q8. Identify the type of model for each case study.
a) Classification

• Predicting "default" or "non-default" (categorical output)7.

b) Regression

• Predicting house prices (continuous output).

c) Clustering

• Segmenting customers into groups based on behavior67.

d) Association Model

• Finding product associations in transactions.

Q9. Type of model for each task:

a) Classification

• Predicting short or long stay (categories).

b) Regression

• Predicting number of days (continuous value).

c) Clustering

• Segmenting patients into groups with similar characteristics.

d) Association Model

• Identifying patterns in treatments and outcomes.

Q10. Convert the scenarios to perceptron:

a) Work-from-home approval decision
• Inputs:
o Employee performs well remotely (Yes=1, No=0)
o Upcoming team meetings/projects (Yes=1, No=0)
o Company policy supports remote work (Yes=1, No=0)
o Beneficial for both (Yes=1, No=0)
• Perceptron output:
o Approve (1) or Deny (0) based on weighted sum of inputs.
b) Solar panel investment decision
• Inputs:
o Sufficient sunlight (Yes=1, No=0)
o Incentives/rebates available (Yes=1, No=0)
o Increases home value (Yes=1, No=0)
o Environmental benefits (Yes=1, No=0)
• Perceptron output:
o Invest (1) or Not Invest (0) based on weighted sum of inputs.