Students can access the CBSE Sample Papers for Class 10 AI with Solutions and marking scheme Set 3 will help students in understanding the difficulty level of the exam.
CBSE Sample Papers for Class 10 AI Set 3 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) Alim is working on a new graphic design project and is trying to choose the best software for his needs. He notices that one software uses icons to represent tools and features, while another uses text-based menus. Alim prefers an interface with easily recognizable symbols. Which type of interface is Alim most likely to favour for his graphic design project?
(a) Text-based menus
(b) Icons
(c) Command-line interface
(d) Pop-up windows
Answer:
(b) Icons
(ii) Which of the following is a benefit of taking a nature walk for stress management?
(a) Increased workload
(b) Reduced physical activity
(c) Improved mood and relaxation
(d) Decreased creativity
Answer:
(c) Improved mood and relaxation
(iii) Which of the following is a significant consequence of increased greenhouse gas emissions?
(a) Decrease in global average temperatures
(b) Improvement in air quality
(c) Rising sea levels and extreme weather events
(d) Enhanced biodiversity
Answer:
(c) Rising sea levels and extreme weather events
(iv) An…………. sentence is a sentence that expressed sudden or strong feelings.
(a) Exclamatory
(b) Assertive
(c) Imperative
(d) Passive
Answer:
(a) Exclamatory
(v) Assertion (A) Regular physical exercise is an effective strategy for managing stress.
Reason (R) Physical exercise releases endorphins, which are natural mood lifters that help reduce stress and improve overall mental well-being.
(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
(vi) Which of the following best represents a strong work ethic for an entrepreneur?
(a) Prioritizing personal gain over team success
(b) Consistently meeting deadlines and maintaining high standards
(c) Delegating all tasks to others without involvement
(d) Avoiding challenges and risks
Answer:
(b) Consistently meeting deadlines and maintaining high standards
Question 2.
Answer any 5 out of the given 6 questions. (1×5=5)
(i) Assertion (A) Artificial intelligence (AI) has the potential to significantly enhance decision-making processes in various domains.
Reason (R) AI algorithms can analyze large datasets, identify complex patterns, and generate insights to inform better decision-making.
(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) The process of adjusting the weights in a neural network to improve performance is called:
(a) Activation
(b) Learning
(c) Optimization
(d) Training
Answer:
(d) Training
Mistake Alert
Many students confuse Optimization with Training. Optimization is part of training where weights are adjusted using techniques like gradient descent. But Training refers to the entire process – including feeding data, calculating loss, and adjusting weights – making it the correct broader term.
(iii) Statement 1 A bias in the training dataset can lead to unfair or inaccurate AI predictions. Statement 2 Ethical evaluation of AI models must consider transparency and the fairness of data sources and model behavior.
(a) Both Statement 1 and Statement 2 are true
(b) Statement 1 is true, Statement 2 is false
(c) Statement 1 is false, Statement 2 is true
(d) Both Statement 1 and Statement 2 are false
Answer:
(a) Both Statement 1 and Statement 2 are true
(iv) ……………. is the process of finding instances of real-world objects in images or videos.
(a) Instance segmentation
(b) Object detection
(c) Classification
(d) Image segmentation
Answer:
(b) Object detection
(v) Words that we want to filter out before doing any analysis of the text are called ……………
(a) Rare words
(b) Stop words
(c) Frequent words
(d) Filter words
Answer:
(b) Stop words
(vi) Ritu is developing an AI model for predicting weather patterns using historical climate data. After training the model, she wants to ensure that it can make reliable predictions on new, unseen data.
Why is it important for Ritu to evaluate her AI model’s performance before deploying it?
(a) To increase the complexity of the model
(b) To visualize the data
(c) To assess how well the chosen model will work in future
(d) To reduce the amount of data used for training
Answer:
(c) To assess how well the chosen model will work in future
Question 3.
Answer any 5 out of the given 6 questions. (5×1=5)
(i) What does discourse integration involve in the context of sentence formation?
(a) Identifying individual words in a sentence
(b) Forming a coherent story within a sentence
(c) Establishing relationships between preceding and succeeding sentences
(d) Applying punctuation and grammar rules to a sentence
Answer:
(c) Establishing relationships between preceding and succeeding sentences
(ii) A neural network with multiple layers of interconnected neurons is called a:
(a) Single-layer network
(b) Deep Neural Network
(c) Linear network
(d) Perceptron
Answer:
(b) Deep Neural Network
(iii) What is the core task of image classification?
(a) Identifying objects and their locations in images
(b) Segmenting objects into individual pixels
(c) Assigning an input image one label from a fixed set of categories
(d) Detecting instances of real-world objects in images
Answer:
(c) Assigning an input image one label from a fixed set of categories
(iv) Identify the logo of an application of AI given below. It helps us to give voice commands and control smart devices.
Answer:
Google Assistant
(v) Which of the following is defined as the measure of balance between precision and recall? (2023)
(a) Accuracy
(b) F1 Score
(c) Reliability
(d) Punctuality
Answer:
(b) F1 Score
(vi) In Reinforcement Learning, how does an agent learn to perform tasks?
(a) By memorizing a dataset of correct answers
(b) By receiving instructions for each step
(c) By exploring actions and receiving feedback in the form of rewards or penalties
(d) By copying other agents actions
Answer:
(c) By exploring actions and receiving feedback in the form of rewards or penalties
Question 4.
Answer any 5 out of the given 6 questions. (5×1=5)
(i) Neural networks are particularly well-suited for tasks involving:
(a) Simple calculations and mathematical operations
(b) Recognizing patterns in complex data like images and text
(c) Performing logical deductions and reasoning tasks
(d) Storing and retrieving large amounts of information
Answer:
(b) Recognizing patterns in complex data like images and text
(ii) Statement 1 A False Negative (FN) occurs when the model incorrectly predicts that a person is not infected, even though they are actually infected.
Statement 2 False Negatives are more dangerous in medical diagnoses than False Positives.
(a) Both Statement 1 and Statement 2 are true
(b) Statement 1 is true, Statement 2 is false
(c) Statement 1 is false, Statement 2 is true
(d) Both Statement 1 and Statement 2 are false
Answer:
(a) Both Statement 1 and Statement 2 are true
(iii) Observe the confusion matrix below and answer the question that follows:
Which of the following evaluation metrics is defined as the fraction of actual positive cases that are correctly identified?
(a) Precision
(b) Accuracy
(c) Recall
(d) F1
Answer:
(c) Recall
Note
Know that Recall = TP / (TP + FN). It measures how well a model captures all actual positive cases, making it essential in medical or fraud detection tasks where missing positives is costly.
(iv) What is the main goal of clustering in unsupervised learning?
(a) To classify data using labeled datasets
(b) To group data points based on similarity
(c) To find cause-effect relationships in data
(d) To train models using rewards and penalties
Answer:
(b) To group data points based on similarity
(v) A platform wants to suggest content to users based on similar listening habits. It uses clustering to group users with similar preferences. Which platform is most likely to use this technique?
(a) Google Docs
(b) YouTube Kids
(c) Spotify
(d) WhatsApp
Answer:
(c) Spotify
(vi) What is the purpose of defining the problem statement during the Problem Scoping stage in an AI project cycle?
(a) To collect data
(b) To understand the aim and objective of the project
(c) To train the model
(d) To process data
Answer:
(b) To understand the aim and objective of the project
Question 5.
Answer any 5 out of the given 6 questions. (5×1=5)
(i) Statement 1 A False Negative in spam email detection occurs when a spam email is mistakenly classified as legitimate.
Statement 2 False Negatives in spam filtering allow spam emails to enter the user’s inbox unnoticed.
(a) Both Statement 1 and Statement 2 are true
(b) Statement 1 is true, Statement 2 is false
(c) Statement 1 is false, Statement 2 is true
(d) Both Statement 1 and Statement 2 are false
Answer:
(a) Both Statement 1 and Statement 2 are true
(ii) 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.
(iii) What is the primary challenge faced by computers in understanding human languages?
(a) Complexity of human languages
(b) Lack of computational power
(c) Incompatibility with numerical data
(d) Limited vocabulary
Answer:
(a) Complexity of human languages
(iv) How do voice assistants utilize NLP?
(a) To analyze visual data
(b) To process numerical data
(c) To understand natural language
(d) To execute tasks based on computer code
Answer:
(c) To understand natural language
(v) In computer vision which of the following tasks is used for multiple objects?
(a) Classification
(b) Classification + Localisation
(c) Instance Segmentation
(d) Localisation
Answer:
(c) Instance Segmentation
(vi) Aditi, a student of class XII developed a chatbot that clarifies the doubts of Economics students. She trained the software with lots of data sets catering to all difficulty levels. If any student would type or ask questions related to Economics, the software would give an instant reply. Identify the domain of AI in the given scenario.
(a) Computer Vision
(b) Data Science
(c) Natural Language Processing
(d) None of the above
Answer:
(c) Natural Language Processing
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.
Sarah is experiencing high levels of stress due to her demanding job, financial worries, and lack of time for personal activities. She finds herself overwhelmed and struggling to manage her responsibilities effectively. What are some factors causing Sarah’s stress, and how might she address them?
Answer:
Sarah’s stress stems from job demands, financial concerns, and inadequate personal time. To address these, she could prioritize tasks, seek financial advice, and schedule regular breaks for relaxation and personal activities, helping to balance her responsibilities and reduce stress.
Question 7.
What to you understand by descriptive feedback?
Answer:
Descriptive feedback provides clear, actionable suggestions tailored to the learner’s specific performance, rather than just a general evaluation. It helps identify strengths and areas for growth, guiding the learner towards more effective strategies and practices.
Question 8.
A city government is implementing a new policy aimed at reducing carbon emissions, promoting renewable energy, and improving waste management. The policy also focuses on enhancing public transportation and green spaces. What is the primary objective of this sustainable development policy?
Answer:
The primary objective of the sustainable development policy is to create a balanced approach that addresses environmental, economic, and social needs. By reducing carbon emissions and promoting renewable energy, the policy aims to ensure long-term ecological health, economic stability, and improved quality of life for residents.
Question 9.
What is the main difference between multitasking and multithreading operating systems?
Answer:
Multitasking OS allows multiple tasks or processes to run simultaneously by managing CPU time among them, whereas multithreading OS involves multiple threads within a single process running concurrently. Multitasking handles different applications or processes at once while multithreading improves efficiency and performance for tasks within the same application.
Question 10.
Why is being open-minded a valuable quality for an entrepreneur?
Answer:
Open-mindedness allows entrepreneurs to explore new ideas, adapt to changes, and embrace innovative solutions. It fosters creativity and helps in understanding diverse perspectives, which can lead to better decision-making and problem-solving, ultimately driving business growth and success.
Answer any 4 out of the given 6 questions in 20-30 words each. (4×2=8)
Question 11.
What is the purpose of image segmentation in computer vision?
Answer:
Image segmentation divides an image into parts or regions to isolate objects or areas of interest, making it easier for computers to analyze specific components separately.
Question 12.
What do you mean by lexical analysis in NLP?
Answer:
Lexical analysis in NLP is the process of breaking down text into its smallest meaningful units (tokens), like words and phrases, to prepare it for further processing.
Question 13.
What is classification accuracy? Can it be used all times for evaluating AI models?
Answer:
Classification accuracy is the percentage of correct predictions made by the model. However, it is not always reliable, especially for imbalanced datasets. In such cases, metrics like precision, recall, and F1-score provide a better evaluation of model performance.
Question 14.
How do real-life examples help in understanding the broader use of AI ?
Answer:
Real-life examples, such as AI in healthcare, agriculture, or transportation, help connect theoretical concepts to practical benefits. They demonstrate how machines can assist humans in diagnosing diseases, monitoring crops, or navigating roads with minimal human input.
Question 15.
Sirisha and Divisha want to make a model which will organise the unlabeled input data into groups based on features. Which learning model should they use and why?
Answer:
Clustering model/Unsupervised learning is used to organise the unlabelled input data into groups based on features.
Clustering is an unsupervised learning algorithm which can cluster unknown data according to the patterns or trends identified out of it. The patterns observed might be the ones which are known to the developer or it might even come up with some unique patterns out of it.
Question 16.
What is supervised, unsupervised and reinforcement learning? Explain with examples.
Answer:
Supervised Learning In supervised learning the model is trained with labeled data to predict outputs (e.g., email spam filtering).
Unsupervised Learning In unsupervised learning the model finds hidden patterns or structures in unlabeled data (e.g., customer segmentation). Reinforcement Learning In this the agent learns by receiving rewards or penalties based on actions taken in an environment (e.g., AI playing a game).
Answer any 3 out of the given 5 questions in 50-80 words each. (3×4=12)
Question 17.
Explain the difference between Machine Learning and Deep Learning with examples.
Answer:
Machine Learning (ML) is a subset of Artificial Intelligence where machines are trained to learn from data and make decisions or predictions without being explicitly programmed. ML models typically require feature extraction by humans and perform well on structured data.
Example A spam email filter that learns from email features (like keywords or sender) to classify emails as spam or not.
Deep Learning (DL) is a specialized branch of Machine Learning that uses artificial neural networks with many layers (hence “deep”). It automatically learns features from unstructured data like images, text, or audio.
Example An image recognition system that detects and classifies objects in pictures without manual feature extraction.
Deep Learning generally requires more data and computing power than traditional Machine Learning but offers higher accuracy in complex tasks.
Question 18.
Observe the given image showing two versions of the same photo: one low-resolution and one high-resolution. Based on this, answer the question that follows.
How do image resolution and pixel values affect the performance of a Computer Vision model?
Answer:
Image resolution refers to the number of pixels in an image, and pixel values represent the brightness or color of each pixel. Higher resolution images have more detail, enabling the model to detect finer features. Accurate pixel values are crucial for tasks like feature extraction and object detection. If the resolution is too low, the model may miss small or subtle patterns, reducing accuracy. Proper resolution and consistent pixel data ensure the CV model performs better across tasks like classification and segmentation.
Question 19.
Consider the following documents:
Document 1: AI is transforming the world
Document 2: AI and ML are changing industries
Implement all the four steps of Bag of Words (BoW) model to create a document vector table.
Answer:
Step 1 Tokenization
Doc1 ai, is, transforming, the, world
Doc2 ai, and, ml, are, changing, industries
Step 2 Vocabulary
[ai, is, transforming, the, world, and, ml, are, changing, industries]
Step 3 Vectorization
| Term | Doc1 | Doc2 |
| ai is transforming the world and ml are changing industries |
1 1 1 1 1 0 0 0 0 0 |
1 0 0 0 0 1 1 1 1 1 |
Question 20.
Explain the three major domains of Artificial Intelligence with suitable real-life applications.
Answer:
The three major domains of Artificial Intelligence are:
- Data Science (Statistical Data and Analysis) This domain focuses on understanding and interpreting large volumes of data using statistical methods. Example Predicting customer buying patterns in e-commerce platforms.
- Computer Vision It enables machines to interpret and analyze visual information from the world such as images or videos.
Example Face recognition systems used in smartphones for unlocking. - Natural Language Processing (NLP) NLP helps computers understand, interpret, and respond to human language (text or speech). Example Chatbots used in customer support or virtual assistants like Alexa and Siri.
Question 21.
You are evaluating a classification model and need to create a confusion matrix. The following values are provided:
- True Positives (TP): 50
- True Negatives (TN): 80
- False Positives (FP): 10
- False Negatives (FN): 15
Create the confusion matrix and explain what each value represents.
Answer:
The confusion matrix would be:
| Predicted Positive |
Predicted Negative |
|
| Actual Positive | 50 (TP) | 15 (FN) |
| Actual Negative | 10 (FP) | 8O(FN) |
In this matrix:
- True Positives (TP) The model correctly predicts 50 positive cases.
- True Negatives (TN) The model correctly predicts 80 negative cases.
- False Positives (FP) The model incorrectly predicts 10 negative cases as positive.
- False Negatives (FN) The model incorrectly predicts 15 positive cases as negative.