Artificial Intelligence - Question Paper 2025 (Code: 104)

← Back to Std 10 Resources | 📥 Download Original PDF

📑 Table of Contents

• Exam Instructions
• Section A - Objective Questions
• Section B - Subjective Questions
• 📚 Study Tips for AI Paper
• Quick Reference Guide
• 📈 Practice Tracker

---

Exam Instructions

• Total Questions: 21 (Section-A: 5 | Section-B: 16)
• Questions to Attempt: 15 (Section-A: 5 | Section-B: 10)
• Maximum Time: 2 Hours
• Maximum Marks: 50 (Section-A: 24 | Section-B: 26)

---

Section – A: Objective Type Questions (24 Marks)

Question 1: Employability Skills

Answer any 4 out of 6 questions
Marks: 4 × 1 = 4

1.(i) Which of the following does not help in stress management?

(A) Healthy food
(B) Sound sleep
(C) Yoga asanas
(D) Negative thoughts

Answer

(D) Negative thoughts

1.(ii) Spam refers to:

(A) Unnecessary images
(B) Temporary files
(C) Junk mails
(D) Music files

Answer

(C) Junk mails

1.(iii) Assertion-Reason Question

Assertion (A): Sustainable agriculture is environment friendly.
Reason (R): It prevents use of chemical fertilizers to protect soil.

(A) Both (A) and (R) are correct and (R) is the correct explanation of (A)
(B) Both (A) and (R) are correct but (R) is not the correct explanation of (A)
(C) (A) is correct but (R) is not correct
(D) (A) is not correct but (R) is correct

Answer

(A) Both (A) and (R) are correct and (R) is the correct explanation of (A)

1.(iv) Which of the following is not a step to build self-motivation?

(A) Focusing on your goal
(B) Planning to achieve your goal
(C) Being indisciplined
(D) Finding out your strength

Answer

(C) Being indisciplined

1.(v) Which type of communication takes place when the number of people is small enough to communicate effectively?

(A) Interpersonal communication
(B) Public communication
(C) Intrapersonal communication
(D) Small group communication

Answer

(D) Small group communication

1.(vi) Reema has started her own restaurant. She keeps trying new ideas for different dishes. As an entrepreneur, Reema is:

(A) Impatient
(B) Creative
(C) Under-confident
(D) Lazy

Answer

(B) Creative

---

Question 2: AI Fundamentals

Answer any 5 out of 6 questions
Marks: 5 × 1 = 5

2.(i) Assertion-Reason Question

Assertion (A): When a machine is able to mimic human traits, it is said to be artificially intelligent.
Reason (R): A fully automatic washing machine is artificially intelligent.

(A) Both (A) and (R) are correct and (R) is the correct explanation of (A)
(B) Both (A) and (R) are correct but (R) is not the correct explanation of (A)
(C) (A) is correct but (R) is not correct
(D) (A) is not correct but (R) is correct

Answer

(C) (A) is correct but (R) is not correct
A washing machine operates on pre-programmed instructions, not AI.

2.(ii) Platforms like Spotify, Facebook, Instagram, Amazon, Netflix show recommendations based on what you like. Which technology is behind this?

(A) Human Intelligence
(B) Platform Intelligence
(C) Artificial Intelligence
(D) Application Intelligence

Answer

(C) Artificial Intelligence

2.(iii) Statement Analysis

Statement 1: In "When" block of 4Ws canvas we find the stakeholders.
Statement 2: Stakeholders are the people who face a particular problem and would be benefitted with the solution.

(A) Both Statement 1 and Statement 2 are correct
(B) Both Statement 1 and Statement 2 are incorrect
(C) Statement 1 is correct but Statement 2 is incorrect
(D) Statement 2 is correct but Statement 1 is incorrect

Answer

(D) Statement 2 is correct but Statement 1 is incorrect
Stakeholders belong to the 'Who' block, not 'When'.

2.(iv) Whenever we want an AI project to be able to predict an output, we need to:

(A) first test it using the data
(B) first train it using the data
(C) Both (A) and (B)
(D) Neither (A) nor (B)

Answer

(B) first train it using the data

2.(v) What does the term "image processing" refer to in Computer Vision?

(A) Editing videos
(B) Extracting meaningful information from images
(C) Playing audio files
(D) Compiling codes

Answer

(B) Extracting meaningful information from images

2.(vi) A corpus contains 4 documents in which words like 'an, is, the' appear frequently. Identify the term used for such words.

(A) Stop word
(B) Rare word
(C) Missing word
(D) Removable word

Answer

(A) Stop word

---

Question 3: Applications & Concepts

Answer any 5 out of 6 questions
Marks: 5 × 1 = 5

3.(i) Identify the logo of an AI application that helps us navigate to places.

Answer

Google Maps

3.(ii) Which data science application is NOT associated with genetics and genomics?

(A) To understand the impact of DNA on health
(B) To analyze reactions to drugs and disease
(C) To find individual biological connection
(D) To search the house address of a relative on the Internet

Answer

(D) To search the house address of a relative on the Internet

3.(iii) In Computer Vision, which task is used for a single object?

(A) Object Detection
(B) Classification + Localization
(C) Instance Segmentation
(D) Non-Localization

Answer

(B) Classification + Localization

3.(iv) Domain-specific language designed for managing data in DBMS, particularly useful for structured data:

(A) SQL
(B) CSV
(C) Spreadsheet
(D) TXT

Answer

(A) SQL

3.(v) Which NLP application provides an overview of a news item or blog post, avoids redundancy, and maximizes content diversity?

(A) Virtual Assistants
(B) Sentiment Analysis
(C) Text Classification
(D) Automatic Summarization

Answer

(D) Automatic Summarization

3.(vi) Which evaluation condition does the following diagram indicate?

(A) False Positive
(B) False Negative
(C) True Positive
(D) True Negative

Answer

(B) False Negative
Prediction: No, Reality: Yes

---

Question 4: Model Evaluation & NLP

Answer any 5 out of 6 questions
Marks: 5 × 1 = 5

4.(i) Correct expansion of CSV:

(A) Comma and Space Value
(B) Comma Separated Values
(C) Control Separated Values
(D) Character Separated Values

Answer

(B) Comma Separated Values

4.(ii) Statement Analysis

Statement 1: Overfitting is not recommended for evaluation of a model.
Statement 2: This is because the model will simply remember the whole training set and will always predict the correct label for any point in the training set.

(A) Both Statement 1 and Statement 2 are correct
(B) Both Statement 1 and Statement 2 are incorrect
(C) Statement 1 is correct but Statement 2 is incorrect
(D) Statement 2 is correct but Statement 1 is incorrect

Answer

(A) Both Statement 1 and Statement 2 are correct

4.(iii) Evaluation parameter defined as the percentage of true positive cases versus all cases where the prediction is true:

(A) Precision
(B) Recall
(C) F1 score
(D) Accuracy

Answer

(A) Precision

4.(iv) Which learning-based approach does the following diagram indicate?

(A) Clustering
(B) Classification
(C) Regression
(D) Dimensionality Reduction

Answer

(B) Classification
The diagram shows a decision boundary separating two distinct classes.

4.(v) Which NLP application is associated with spam filtering in emails?

(A) Virtual Assistants
(B) Sentiment Analysis
(C) Text Classification
(D) Automatic Summarization

Answer

(C) Text Classification

4.(vi) Raghav can turn on/off appliances remotely using an internet-enabled device. This is an example of:

(A) Artificial Intelligence (AI)
(B) Internet of Things (IoT)
(C) Computer Vision (CV)
(D) Deep Learning (DL)

Answer

(B) Internet of Things (IoT)

---

Question 5: Advanced Concepts

Answer any 5 out of 6 questions
Marks: 5 × 1 = 5

5.(i) Musical intelligence is a concept that:

(A) assesses one's ability to regulate, measure and understand numerical symbols, abstraction and logic
(B) measures language processing skills in understanding or implementation in writing or verbally
(C) evaluates the ability to process information on the environment around us
(D) describes a person's ability to recognize and create sounds, rhythms and sound patterns

Answer

(D) describes a person's ability to recognize and create sounds, rhythms and sound patterns

5.(ii) With respect to evaluation, for which does the prediction and reality match?

(A) True positive and False positive
(B) True positive and True negative
(C) False positive and False negative
(D) True positive and False negative

Answer

(B) True positive and True negative

5.(iii) Statement Analysis

Statement 1: Various search engines and e-commerce portals now have image-based search using computer vision.
Statement 2: Image-based search helps in finding items, people and places by giving their sounds to the system.

(A) Both Statement 1 and Statement 2 are correct
(B) Both Statement 1 and Statement 2 are incorrect
(C) Statement 1 is correct but Statement 2 is incorrect
(D) Statement 2 is correct but Statement 1 is incorrect

Answer

(C) Statement 1 is correct but Statement 2 is incorrect

5.(iv) In NLP, which word represents a stem resulting from stemming for "Studies"?

(A) Study
(B) Stud
(C) Studi
(D) Studied

Answer

(C) Studi

5.(v) Which scenario might have a high False Negative (FN) cost?

(A) Viral Disease Outbreak
(B) Spam
(C) Mining
(D) Image Search

Answer

(A) Viral Disease Outbreak

5.(vi) Which type of chatbot has wide functionality, is flexible and powerful, and works on bigger databases directly?

(A) Rule-based Bot
(B) Script-based Bot
(C) AI-Bot / Smart Bot
(D) Menu-based Bot

Answer

(C) AI-Bot / Smart Bot
AI-powered conversational bots (not simple rule-based script bots).

---

Section – B: Subjective Type Questions (26 Marks)

Employability Skills

Answer any 3 out of 5 questions
Word Limit: 20-30 words each
Marks: 3 × 2 = 6

Q6. Explain the importance of following a healthy lifestyle in effectively dealing with stress. Write any one common factor that causes stress among children nowadays.

Answer

A healthy lifestyle, including proper diet and adequate sleep, builds physical and mental resilience, reducing the impact of stress. A common factor causing stress among children is academic pressure or peer pressure.

Q7. If you are a team leader of 20 people in an organization, mention any two methods for effective communication with your team members.

Answer

1. Regular team meetings for transparent, open discussions
2. Digital collaboration tools (emails, group chats, project management software) to ensure seamless information flow

Q8. Write any two tasks that entrepreneurs do when they run their business.

Answer

1. Innovation: Constantly create new products or services to meet market needs
2. Risk Management: Manage business risks and resources (financial and human) to ensure growth

Q9. Enlist any two measures that an individual should follow to take care of his/her digital devices.

Answer

1. Physically protect devices from extreme temperatures and liquid spills
2. Install reliable antivirus software and update the OS regularly to prevent malware

Q10. Discuss the following problems related to sustainable development: (i) Water (ii) Fuel

Answer

(i) Water: Over-extraction and pollution lead to severe water scarcity and contaminated drinking supplies.
(ii) Fuel: Heavy reliance on non-renewable fossil fuels drives rapid climate change and depletes finite energy sources.

---

Short Answer Questions

Answer any 4 out of 6 questions
Word Limit: 20-30 words each
Marks: 4 × 2 = 8

Q11. Differentiate between Computer Vision (CV) and Natural Language Processing (NLP).

Answer

Computer Vision (CV) enables machines to acquire, process, and interpret visual data (images/videos).
Natural Language Processing (NLP) allows machines to understand, interpret, and generate human text and speech.

Q12. Define with respect to AI project cycle: (i) Data Exploration (ii) Data Features

Answer

(i) Data Exploration: The process of analyzing data visually and statistically to uncover trends, patterns, and anomalies.
(ii) Data Features: The specific, measurable attributes or variables in a dataset used to train an AI model.

Q13. One application of Data Science is Airline Route Planning. List any two tasks that airline companies can do using Data Science.

Answer

1. Predict passenger demand to optimize flight schedules and pricing
2. Analyze weather and air traffic data to plot the most fuel-efficient and safe routes

Q14. Give any two key impacts of Computer Vision on medical imaging.

Answer

1. Accurately detects anomalies like tumors in X-rays or MRIs much faster than human eyes
2. Aids in creating 3D visualizations for pre-surgical planning and minimally invasive procedures

Q15. What is the primary difference between Human Language and Computer Language?

Answer

Human language is complex, relies heavily on context and tone, and contains ambiguities.
Computer language operates on strict, predefined syntax and unambiguous rules that must be explicitly followed.

Q16. Suppose you are developing an AI model to detect fraudulent financial transaction risk. Describe False Positives and False Negatives in this context.

Answer

False Positive: A genuine transaction is incorrectly blocked as fraudulent, causing customer frustration and inconvenience.
False Negative: A truly fraudulent transaction goes undetected, leading to financial loss and security breach.

---

Long Answer Questions

Answer any 3 out of 5 questions
Word Limit: 50-80 words each
Marks: 3 × 4 = 12

Q17. What do you understand by AI Bias and AI Access? Give one example of each to support your answer.

Answer

AI Bias occurs when an AI system produces prejudiced results due to flawed assumptions in the machine learning process or skewed training data.
Example: A facial recognition system failing to accurately identify people of color because it was trained predominantly on lighter-skinned faces.

AI Access refers to the gap in availability and affordability of AI technologies among different socioeconomic groups.
Example: Students in well-funded urban schools utilizing AI tutors, while rural students lack basic internet access, widening the educational divide.

Q18. What is the use of problem statement template with respect to 4Ws of problem scoping? Draw a problem statement template depicting all key elements.

Answer

The 4Ws Problem Canvas provides a structured framework to define an AI problem clearly before building a solution. It breaks the problem into manageable scopes to prevent project deviation.

Problem Statement Template: - Who: Who are the stakeholders experiencing the problem? - What: What is the specific nature of the problem? - Where: In what context or location does the problem occur? - When: At what time or situation is the problem prominent?

Q19. Consider the following diagram. It explains how a system of organized machine learning algorithms perform certain tasks. Identify the concept and explain its working.

Answer

The diagram represents Artificial Neural Networks / Deep Learning.

Working: - Raw data passes through interconnected nodes containing machine learning algorithms - The crossing lines represent weighted connections that transfer data between layers - Hidden layers autonomously extract complex features and patterns from the data - These "Hidden Rules" process information through multiple layers - The final layer generates the prediction or "Answer" based on learned patterns

Q20. Consider the following documents:

Document 1: NLP is a domain of AI.
Document 2: NLP stands for Natural Language Processing.

Implement all four steps of Bag of Words (BoW) model to create a document vector table.

Answer

Step 1: Text Normalization (Lowercasing and removing punctuation)
- Doc 1: "nlp is a domain of ai"
- Doc 2: "nlp stands for natural language processing"

Step 2: Tokenization (Splitting into individual words)

Step 3: Creating Vocabulary (Unique sorted words)
Vocabulary: [a, ai, domain, for, is, language, natural, nlp, of, processing, stands]

Step 4: Creating Document Vectors (Counting word frequencies)
- Doc 1 Vector: [1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0]
- Doc 2 Vector: [0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1]

Q21. An AI model was tested on 630 specimens to diagnose ailments. The confusion matrix is:

	Reality: Yes	Reality: No
Prediction: Yes	110	60
Prediction: No	50	410

(A) How many total cases are True Negative?
(B) Calculate Precision, Recall, and F1 Score.

Answer

(A) True Negatives: 410 (Prediction: No, Reality: No)

(B) Calculations: - True Positive (TP) = 110 - False Positive (FP) = 60 - False Negative (FN) = 50

Precision = TP / (TP + FP) = 110 / (110 + 60) = 110/170 = 0.647 (64.7%)

Recall = TP / (TP + FN) = 110 / (110 + 50) = 110/160 = 0.6875 (68.75%)

F1 Score = 2 × (Precision × Recall) / (Precision + Recall)
= 2 × (0.647 × 0.6875) / (0.647 + 0.6875)
= 0.666 (66.6%)

---

📚 Study Tips for AI Paper

⏰ Time Management

• Section A: ~45 minutes (24 marks) - Quick objective questions
• Section B: ~75 minutes (26 marks) - Detailed subjective answers
• Review Time: Keep 10-15 minutes for revision

🎯 Key Topics to Focus

• AI Fundamentals & Applications (Q2, Q3)
• Model Evaluation Metrics (Q4, Q21)
• NLP & Computer Vision basics (Q3, Q4, Q20)
• 4Ws Problem Canvas (Q2.iii, Q18)
• Confusion Matrix concepts (Q3.vi, Q4.iii, Q21)

📝 Question Paper Strategy

• Start with familiar topics to build confidence
• Don't skip assertion-reason questions (they're scoring!)
• Practice diagram-based questions thoroughly
• For Bag of Words, remember the 4-step process
• Memorize key formulas for evaluation metrics

🔍 Common Mistakes to Avoid

• Confusing Precision with Recall
• Mixing up True Positive/False Positive
• Forgetting to normalize text in NLP
• Not reading assertion-reason questions carefully

---

Quick Reference Guide

Key Formulas

Precision = TP / (TP + FP)
Recall = TP / (TP + FN)
F1 Score = 2 × (Precision × Recall) / (Precision + Recall)

Confusion Matrix Terms

• True Positive (TP): Prediction = Yes, Reality = Yes
• True Negative (TN): Prediction = No, Reality = No
• False Positive (FP): Prediction = Yes, Reality = No (Type I Error)
• False Negative (FN): Prediction = No, Reality = Yes (Type II Error)

4Ws Problem Canvas

Element	Description	Example Question
Who	Stakeholders facing the problem	"Who are the stakeholders experiencing the problem?"
What	Nature of the problem	"What is the specific nature of the problem?"
Where	Context/location of problem	"In what context or location does the problem occur?"
When	Time/situation of occurrence	"At what time or situation is the problem prominent?"

Common AI Terms

• Corpus: Collection of documents for NLP analysis
• Stemming: Reducing words to their root form (e.g., "Studies" → "Studi")
• Tokenization: Breaking text into individual words/tokens
• Stop Words: Common words like 'an', 'is', 'the' that are often removed
• Overfitting: When model memorizes training data instead of learning patterns

Bag of Words (BoW) - 4 Step Process

1. Text Normalization: Lowercase and remove punctuation
2. Tokenization: Split into individual words
3. Vocabulary Creation: List of unique sorted words
4. Document Vectors: Count word frequencies for each document

Question Paper Pattern

Section	Question Types	Marks	Time Allotment
A	Objective (MCQ, Assertion-Reason)	24	~45 minutes
B	Subjective (Short & Long Answers)	26	~75 minutes

---

📈 Practice Tracker

Use this checklist to track your preparation progress:

Section A - Objective Questions (24 marks)

• Q1: Employability Skills (6 questions, attempt 4)
• Q2: AI Fundamentals (6 questions, attempt 5)
• Q3: Applications & Concepts (6 questions, attempt 5)
• Q4: Model Evaluation & NLP (6 questions, attempt 5)
• Q5: Advanced Concepts (6 questions, attempt 5)

Section B - Subjective Questions (26 marks)

• Q6-Q10: Employability Skills (5 questions, attempt 3)
• Q11-Q16: Short Answer Questions (6 questions, attempt 4)
• Q17-Q21: Long Answer Questions (5 questions, attempt 3)

📊 Overall Progress

• Total Questions to Attempt: 15/21
• Target Score: 40+ marks out of 50
• Practice Sessions Completed: ___/10
• Mock Tests Taken: ___/3

🎯 Revision Checklist

• Reviewed all AI Fundamentals concepts
• Practiced confusion matrix calculations
• Memorized key formulas (Precision, Recall, F1)
• Understood 4Ws Problem Canvas
• Practiced Bag of Words implementation
• Reviewed common AI terminology

---

🔗 Related Resources

• CBSE Class 10 Main Page
• Download Original Question Paper PDF
• More CBSE Study Materials

---

End of Question Paper