Here are the exam-oriented answers in question-answer format for the questions
visible in your images:
15 Questions of 2 Marks Each (15 x 2 = 30)
Q21. Write down some applications of AI in daily life.
Ans: Applications of AI in daily life include virtual assistants like Siri and Alexa,
recommendation systems on YouTube and Netflix, Google Maps for navigation,
chatbots in customer service, and face recognition in smartphones.
Q22. How should AI systems maintain privacy of user data?
Ans: AI systems should use techniques like data encryption, anonymization, secure
data storage, and follow legal frameworks like GDPR to ensure user data privacy.
Q23. State the requirement of NLP. Give example.
Ans: NLP is required to enable machines to understand, interpret, and respond in
human language. Example: Chatbots that respond to customer queries.
Q24. Why is ethics important while developing AI applications? Justify your answer.
Ans: Ethics ensures AI systems are fair, non-discriminatory, and respect user rights. It
builds trust and avoids harm. For example, biased hiring AI can unfairly reject
candidates.
Q25. How can biasness influence AI systems? Give suitable example.
Ans: Bias can lead to unfair decisions. For example, if a loan approval AI is trained
on biased data, it may reject applications from a specific community.
Q26. What do you mean by AI project cycle? State its advantages.
Ans: AI project cycle is a step-by-step approach to develop AI solutions. It helps in
organized problem-solving, reducing errors, and ensures success.
Q27. Name the stages of AI project cycle.
Ans: The stages are: Problem Scoping, Data Acquisition, Data Exploration,
Modeling, and Evaluation.
Q28. Explain the concept of 4W’s problem canvas.
Ans: 4W’s problem canvas includes Who, What, Where, and Why—used to
understand the problem deeply before building an AI solution.
Q29. Sunita needs to collect data for her AI project. Please suggest her any 4 methods
of Data Acquisition.
Ans: Methods include: Surveys, Sensors, Web Scraping, and Existing Databases.
Q30. Distinguish between Training data and Testing data.
Ans: Training data is used to train the model; testing data is used to check model
accuracy. Training data helps the model learn; testing data checks its performance.
Q31. Ravi needs to represent data. State any two data visualization techniques during
data exploration.
Ans: Bar graphs and Pie charts are common visualization techniques.
Q32. Differentiate between Supervised and Unsupervised Learning.
Ans: Supervised learning uses labeled data; unsupervised learning uses unlabeled
data. Example: Supervised – Email spam detection; Unsupervised – Customer
segmentation.
Q33. How is Reinforcement Learning implemented?
Ans: It is implemented by allowing agents to interact with an environment and learn
from feedback (rewards or penalties) to make better decisions over time.
Q34. Write down the importance of Evaluation in AI project cycle.
Ans: Evaluation ensures the AI model performs well, is accurate, reliable, and meets
project goals before deployment.
Q35. Name any two methods of AI project evaluation.
Ans: Confusion Matrix and Accuracy Score.
5 Questions of 4 Marks Each (5 x 4 = 20)
Q36. Define AI, ML, and DL. Also state the relation among them.
Ans: AI (Artificial Intelligence) is the science of making machines smart. ML
(Machine Learning) is a subset of AI that enables machines to learn from data. DL
(Deep Learning) is a subset of ML that uses neural networks for complex tasks. So,
DL ⊂ ML ⊂ AI.
Q37. What do you mean by Data Science and Computer Vision? Give suitable
examples for each.
Ans: Data Science involves analyzing large datasets for insights, e.g., predicting
customer behavior. Computer Vision allows machines to interpret images or videos,
e.g., face detection in smartphones.
Q38. Distinguish between Rule-based AI and Learning-based AI.
Ans: Rule-based AI follows predefined rules, e.g., expert systems. Learning-based AI
learns patterns from data, e.g., recommendation systems.
Q39. Explain the concept of Regression and Classification. Give examples for each.
Ans: Regression predicts continuous values (e.g., house prices). Classification
predicts categories (e.g., spam or not spam emails).
Q40. How is clustering different from classification? When is dimensionality
reduction useful?
Ans: Clustering groups similar items without labels; classification uses labeled data.
Dimensionality reduction is useful when data has too many features, helping in
reducing complexity and improving model performance.
