Students can access the CBSE Sample Papers for Class 10 AI with Solutions and marking scheme Set 5 will help students in understanding the difficulty level of the exam.
CBSE Sample Papers for Class 10 AI Set 5 with Solutions
General Instructions
- Please read the instructions carefully.
- This Question Paper consists of 21 questions in two sections: Section A & Section B.
- Section A has Objective type questions whereas Section B contains Subjective type questions.
- Out of the given (5+16)=21 questions, a candidate has to answer (5+10)=15 questions in the allotted (maximum) time of 2 hours.
- All questions of a particular section must be attempted in the correct order.
- Section A: Objective Type Questions (24 Marks)
- This section has 5 questions.
- There is no negative marking.
- Do as per the instructions given.
- Marks allotted are mentioned against each question/part.
- Section B: Subjective Type Questions (26 Marks)
- This section has 16 questions.
- A candidate has to do 10 questions.
- Do as per the instructions given.
- Marks allotted are mentioned against each question/part.
Section A
Objective Type Questions
Question 1.
Answer any 4 out of the given 6 questions on Employability Skills. (4×1=4)
(i) How can an antivirus protect your device?
(a) It can protect it from over-heating.
(b) It can increase its performance
(c) It can prevent data from getting corrupt.
(d) It can backup data.
Answer:
(c) It can prevent data from getting corrupt.
(ii) Which of the following is true about effective communication?
(a) It enhances clarity and understanding between individuals.
(b) It primarily focuses on using complex vocabulary to impress the audience.
(c) Both (a) and (b) are true.
(d) Both (a) and (b) are false.
Answer:
(a) It enhances clarity and understanding between individuals.
(iii) High expectations from self can leave one with chronic anxiety and stress, thus leading to ………. stress.
(a) physical
(b) emotional
(c) mental
(d) financial
Answer:
(c) mental
(iv) Assertion (A) Organic farming helps in achieving sustainable development goals.
Reason (R) Organic farming avoids synthetic chemicals and promotes eco-friendly practices that protect soil, water, and biodiversity.
(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
(v) Which of the following questions is most effective for self-reflection and understanding your strengths?
(a) What do others think of my work?
(b) What activities make me feel most fulfilled and energized?
(c) How can I impress my colleagues?
(d) What skills do I need to develop to get a promotion?
Answer:
(b) What activities make me feel most fulfilled and energized?
(vi) Ramesh recently started a small business. He noticed that managing finances and taking risks are major parts of being an entrepreneur.
Which of the following statements best describes a common challenge faced by entrepreneurs?
(a) Entrepreneurs always have predictable and stable income.
(b) Entrepreneurs are guaranteed immediate success with minimal effort.
(c) Entrepreneurs often face financial uncertainty and high risk, especially in the early stages.
(d) Entrepreneurs have unlimited time for leisure and personal activities.
Answer:
(c) Entrepreneurs often face financial uncertainty and high risk, especially in the early stages.
Question 2.
Answer any 5 out of the given 6 questions (5×1=5)
(i) Assertion (A) Face lock in smartphones uses Computer Vision to unlock the phone. Reason (R) The smartphone’s front camera captures and stores the user’s facial features, which are then compared during unlocking attempts.
(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
(ii) Which of the following is not part of the AI Project Cycle?
(a) Data Exploration
(b) Modelling
(c) Testing
(d) Problem Scoping
Answer:
(c) Testing
(iii) Statement 1 AI accountability means that developers and organizations should take responsibility for the consequences of AI decisions.
Statement 2 AI systems should be allowed to operate without any human oversight to ensure efficiency.
(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
(iv) Which of the following statements is TRUE about the Rule-Based Chatbot for Order Tracking described in the scenario?
(a) It uses a large dataset to learn and predict user queries.
(b) It adapts automatically to new types of user queries without predefined rules.
(c) It follows specific predefined rules to respond to user queries about order tracking.
(d) It can handle complex and uncertain situations efficiently.
Answer:
(c) It follows specific predefined rules to respond to user queries about order tracking.
(v) Renu is a radiologist who uses AI tools to analyze medical scans. These tools help her detect issues more quickly and accurately, making diagnosis more efficient.
How has Artificial Intelligence enhanced medical imaging?
(a) By replacing radiologists completely
(b) By improving diagnostic accuracy and efficiency
(c) By eliminating the need for scans
(d) By storing records in the cloud
Answer:
(b) By improving diagnostic accuracy and efficiency
(vi) What is the process of converting words into their base or root from called?
(a) Tokenization
(b) Stemming
(c) Lemmatization
(d) Part-of-speech tagging
Answer:
(b) Stemming
Question 3.
Answer any 5 out of the given 6 questions. (5×1=5)
(i) What is the purpose of the Bag-of-Words (BoW) model in NLP?
(a) To represent words as vectors
(b) To calculate word frequencies
(c) To identify syntactic dependencies
(d) To perform sentiment analysis
Answer:
(b) To calculate word frequencies
(ii) The result of comparison between the prediction and reality can be recorded in what we call the ……..
(a) Overfitting
(b) Problem Scoping
(c) Confusion Matrix
(d) Data acquisition
Answer:
(c) Confusion Matrix
(iii) Which of the following algorithms is commonly used for image classification?
(a) K -means clustering
(b) Decision trees
(c) Convolutional Neural Networks (CNN)
(d) Support Vector Machines (SVM)
Answer:
(c) Convolutional Neural Networks (CNN)
(iv) Identify the logo of an AI-powered application used for language translation. It helps users translate text, speech, and images in real-time.
Answer:
Google Translate
(v) What is the primary role of data in an email spam filter that uses a learning-based approach?
(a) To display emails in the inbox
(b) To label emails as important or not
(c) To train the system by providing examples of spam and not spam
(d) To delete all spam emails automatically
Answer:
(c) To train the system by providing examples of spam and not spam
(vi) Reinforcement Learning is particularly useful for scenarios where:
(a) Large amounts of labeled data are available.
(b) The desired outcome is clear, but the path to achieve it is unknown.
(c) The data is structured and easily categorized.
(d) The task requires reasoning and logical deduction.
Answer:
(b) The desired outcome is clear, but the path to achieve it is unknown.
Question 4.
Answer any 5 out of the given 6 questions (5×1=5)
(i) What is the main purpose of a training data set in machine learning?
(a) To evaluate the model’s accuracy
(b) To test students’ performance
(c) To teach the AI model by identifying patterns and making predictions
(d) To label the output of the model manually
Answer:
(c) To teach the AI model by identifying patterns and making predictions
(ii) What does a confusion matrix compare in a classification model?
(a) Predicted outputs with algorithm speed
(b) Actual values with predicted values
(c) Training data with testing data
(d) Data size with model accuracy
Answer:
(b) Actual values with predicted values
(iii) Statement 1 AI models can develop biases if the training data is not diverse.
Statement 2 A biased AI model may lead to unfair predictions and discrimination.
(a) Statement 1 is true, Statement 2 is false
(b) Statement 1 is false, Statement 2 is true
(c) Both Statement 1 and Statement 2 are true, and Statement 2 is the correct explanation of Statement 1
(d) Both Statement 1 and Statement 2 are true, but Statement 2 is not the correct explanation of Statement 1
Answer:
(c) Both Statement 1 and Statement 2 are true, and Statement 2 is the correct explanation of Statement 1
(iv) Which form of learning based approach does the following diagram indicate?
(a) Supervised
(b) Clustering
(c) Classification
(d) Regression
Answer:
(c) Classification
(v) How is a testing data set used in AI model development?
(a) To provide more examples for training
(b) To increase the model’s memory
(c) To evaluate the performance of the trained model
(d) To store unused data
Answer:
(c) To evaluate the performance of the trained model
(vi) Sneha adjusts the temperature of her home air conditioner using her smartphone while she is at work. This is an example of:
(a) Cloud Computing
(b) Internet of Things (IoT)
(c) Artificial Intelligence
(d) Data Mining
Answer:
(b) Internet of Things (IoT)
Question 5.
Answer any 5 out of the given 6 questions (5×1=5)
(i) A high F1 score generally suggests:
(a) The model has low precision and low recall
(b) The model has high precision but low recall
(c) The model has low precision but high recall
(d) The model has both high precision and high recall
Answer:
(d) The model has both high precision and high recall
Note
Understand that F1 score is the harmonic mean of precision and recall, making it a key indicator of overall model performance in classification problems. It is especially useful when classes are imbalanced.
(ii) In a confusion matrix, which term represents the model correctly predicting a positive case?
(a) False Positive (FP)
(b) True Negative (TN)
(c) True Positive (TP)
(d) False Negative (FN)
Answer:
(c) True Positive (TP)
(iii) Statement 1 A pixel is defined as the smallest element of a digital image. Statement 2 Pixel resolution is the total pixel count in a digital image.
(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
(iv) Which technique aims to identify and extract the main ideas or topics from a collection of documents?
Answer:
Document clustering
(v) In the context of COVID-19 detection using AI, why is Recall considered the preferred metric?
(a) It measures the number of people not infected.
(b) It focuses on correctly identifying all Negative cases.
(c) It helps in reducing False Positives to avoid unnecessary treatment.
(d) It helps in minimizing False Negatives, ensuring affected individuals are correctly identified.
Answer:
(d) It helps in minimizing False Negatives, ensuring affected individuals are correctly identified.
(vi) Which method is used to assign a sentiment label to a given text?
(a) Named entity recognition
(b) Sentiment analysis
(c) Part-of-speech tagging
(d) Dependency parsing
Answer:
(b) Sentiment analysis
Section B
Subjective Type Questions
Answer any 3 out of the given 5 questions on Employability skills. Answer each question in 20-30 words. (3×2=6)
Question 6.
Manya is a recent graduate aiming to work in environmental management. She has a strong interest in sustainability but lacks specific training in green technologies and practices. How can Manya develop relevant green skills for her career?
Answer:
Manya can develop green skills by pursuing certifications in sustainable practices, attending workshops on green technologies, and gaining hands-on experience through internships or volunteer work in environmental projects. These actions will enhance her knowledge and make her more competitive in the field of environmental management.
Question 7.
How often should you perform a maintenance check on your computer to ensure optimal performance?
Answer:
It is recommended to perform a maintenance check on your computer every 3 to 6 months. This includes cleaning dust from components, updating software, running antivirus scans, and checking for hardware issues. Regular maintenance helps prevent performance degradation and extends the lifespan of your computer.
Question 8.
Arpit is passionate about painting but struggles with basic drawing techniques. His friend suggests he consider a career in graphic design, but Arpit is unsure whether his interest in art aligns with his abilities. How can Arpit differentiate between his interest and his abilities?
Answer:
Arpit should evaluate his skills and performance in drawing versus his passion for painting. Interests reflect what he enjoys, while abilities are about his proficiency. By assessing his skills in various art forms and seeking feedback, Arpit can better align his career choice with his capabilities.
Question 9.
What is a common myth about entrepreneurship?
Answer:
A common myth about entrepreneurship is that it guarantees quick and easy financial success. In reality, entrepreneurship involves significant risks, long hours, and often years of hard work before achieving profitability. The journey requires perseverance and resilience, and success is rarely immediate or effortless.
Question 10.
How does facial expression impact effective communication?
Answer:
Facial expressions play a crucial role in effective communication by conveying emotions and reinforcing the spoken message. They help to express feelings like happiness, sadness, or anger, thus providing context and enhancing mutual understanding between the communicator and the audience.
Answer any 4 out of the given 6 questions in 20-30 words each. (4×2=8)
Question 11.
Mention the factors which knowingly or unknowingly influence our decision-making.
Answer:
Factors influencing decision-making include:
- Cognitive biases (e.g., confirmation bias, anchoring bias)
- Emotions and psychological state
- Social influences and peer pressure
- Past experiences and learned behavior
- Availability of information and misinformation
- Time constraints and urgency
- Personal values and ethics
Question 12.
Outline the main steps in the AI Project Cycle briefly.
Answer:
The AI Project Cycle consists of five main steps:
- Problem Scoping understanding the problem.
- Data Acquisition collecting and processing relevant data.
- Data Exploration arranging the data uniformly.
- Modelling creating models from the data.
- Evaluation evaluating the project.
Question 13.
Give difference between rule based and learning based AI models.
Answer:
- Rule-Based AI Models Use predefined rules and logic to make decisions. They don’t learn from data and require manual updates.
- Learning-Based AI Models Learn from data, adapt over time, and improve performance by recognizing patterns from large datasets.
Question 14.
Enlist two smartphone apps that utilize computer vision technology? How have these apps improved your efficiency or convenience in daily tasks?
Answer:
Two smartphone apps that utilize computer vision technology are:
- Google Lens It recognizes objects, text, and landmarks.
Efficiency It can instantly translates text, searches for objects, and identifies plants/animals. - Face ID (Apple) It uses facial recognition for unlocking devices.
Convenience It provides fast and secure authentication without using passwords.
Question 15.
Describe two practical uses of Natural Language Processing in real-world scenarios.
Answer:
Sentiment Analysis Analyzing customer reviews or social media posts to understand public opinion about products or services.
Chatbots/Virtual Assistants Providing automated customer support or answering queries through natural language conversations.
Question 16.
What is the primary function of hidden layers in a deep learning model?
Answer:
Hidden layers in a deep learning model extract and refine features from input data, gradually identifying patterns such as edges, shapes, and complex structures to improve classification accuracy.
Answer any 3 out of the given 5 questions in 50-80 words each. (3×4=12)
Question 17.
Mention the key characteristics of sector-based frameworks.
Answer:
Sector-based frameworks are:
- Industry-Specific Tailored to particular sectors (e.g., healthcare, finance, education).
- Regulatory Compliant Align with laws and policies governing the sector.
- Risk-Oriented Address industry-specific risks and challenges.
- Guideline-Driven Provide structured guidelines for implementation.
- Stakeholder-Focused Consider the needs of businesses, consumers, and regulators.
Question 18.
What are the core subcategories under supervised and unsupervised learning?
Answer:
Supervised learning includes classification and regression models, where data comes with predefined labels or values. Classification models sort data into categories, while regression models predict continuous outcomes.
Unsupervised learning includes clustering and association models, which find patterns or relationships in unlabeled data. Sessions focused on these subcategories explain their applications and differences, helping learners understand how data is structured and how machines identify insights without explicit instructions.
Question 19.
Observe the image below and answer the following question:
Based on the diagram shown, explain what is meant by the train-test split. Give an example to support your explanation.
Answer:
The train-test split is a method used to evaluate machine learning models by dividing the dataset into two parts:
Training Set Used to train the model.
Test Set Used to evaluate the model’s performance on unseen data.
Example
Suppose we have a dataset of 10,000 customer transactions for fraud detection. We split the dataset into:
80%( 8000 transactions) as the training set to teach the model.
20% (2000 transactions) as the test set to assess its accuracy.
If the model performs well on the test set, it is likely to work well in real-world scenarios.
Question 20.
What are the key steps in implementing the Bag of Words (BoW) model?
Answer:
The key steps in implementing the Bag of Words (BoW) model are
- Tokenization Break the text into individual words or tokens.
- Vocabulary Creation Build a dictionary of unique words from the text corpus.
- Vectorization Represent each document as a vector with the frequency of each word from the vocabulary.
- Feature Matrix Formation Create a matrix where each row corresponds to a document and each column to a word from the vocabulary, with cell values indicating word frequencies.
- Normalization Adjust the vectors for better performance, often by applying techniques such as TF-IDF to reflect the importance of words in the documents.
Question 21.
You have built a binary classification model to predict whether emails are spam or not. After evaluating the model, you find the following results: 50 true positives, 10 false positives, 30 true negatives, and 10 false negatives.
(a) How would you create a confusion matrix based on these results?
(b) What does FP reveal?
Answer:
(a) To create a confusion matrix, organize the results into a 2×2 matrix format:
- True Positives (TP): 50
- False Positives (FP): 10
- True Negatives (TN): 30
- False Negatives (FN): 10
The matrix would look like this:
| Predicted Positive |
Predicted Negative |
|
| Actual Positive | 50 (TP) | 10(FN) |
| Actual Negative | 10 (FP) | 30(TN) |
(b) False Positives (FP) reveal the number of emails that were incorrectly classified as spam when they are actually not spam. This indicates how often the model mistakenly identifies legitimate emails as spam, leading to potential inconvenience for users who may miss important emails.