Students can access the CBSE Sample Papers for Class 10 AI with Solutions and marking scheme Set 2 will help students in understanding the difficulty level of the exam.
CBSE Sample Papers for Class 10 AI Set 2 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) Jiya is using her Windows 11 computer and notices that she cannot see the icon for her antivirus software in the notification area. She recently updated her antivirus software.
What is the most likely reason for this issue?
(a) Antivirus software has been uninstalled automatically
(b) System is infected with a virus hiding the antivirus icon
(c) The antivirus icon is hidden in the taskbar settings after update
(d) Windows is not compatible with any antivirus software
Answer:
(c) The antivirus icon is hidden in the taskbar settings after update
(ii) Which of the following is a common stress-causing agent?
(a) Regular exercise
(b) Balanced diet
(c) High workload
(d) Adequate sleep
Answer:
(c) High workload
(iii) Which of the following is a key principle of sustainable urban development?
(a) Increasing car dependency
(b) Expanding urban sprawl
(c) Promoting public transportation
(d) Reducing green spaces
Answer:
(c) Promoting public transportation
(iv) What is the primary role of eye contact in non-verbal communication?
(a) To show dominance
(b) To indicate attentiveness
(c) To avoid interaction
(d) To distract the speaker
Answer:
(b) To indicate attentiveness
(v) Identifying personal weaknesses can help in self-improvement. What is a common approach to recognizing your weaknesses?
(a) Ignoring feedback
(b) Seeking constructive criticism
(c) Avoiding self-reflection
(d) Comparing yourself to others
Answer:
(b) Seeking constructive criticism
(vi) Assertion (A) Entrepreneurship often involves identifying and exploiting market gaps.
Reason (R) Entrepreneurs frequently succeed by spotting unmet needs or inefficiencies in the market and developing innovative solutions to address them. This ability to recognize opportunities where others see challenges is a key factor in their success.
(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
Question 2.
Answer any 5 out of the given 6 questions. (5×1=5)
(i) Assertion (A) Supervised learning is a type of machine learning where the model is trained on labeled data.
Reason (R) In supervised learning, the model learns from input-output pairs, where each input data point is associated with a corresponding output label.
(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) Statement 1 Unsupervised learning uses labeled datasets to train algorithms to predict outcomes and recognize patterns.
Statement 2 In unsupervised learning, the training data provided to the machines work as the supervisor.
(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:
(b) Both Statement 1 and Statement 2 are incorrect
(iii) Search engines not only predict what popular searches may apply to your query as you start typing, but it looks at the whole picture and recognizes what you’re trying to say rather than the exact search words. This is an example of
(a) Computer Vision
(b) Data Sciences
(c) Natural Language Processing
(d) Natural Language Understanding
Answer:
(d) Natural Language Understanding
(iv) In Deep Learning, what is the role of hidden layers?
(a) To directly produce the final output
(b) To store and retrieve training data
(c) To learn different features of the input data step by step
(d) To reduce the complexity of computations
Answer:
(c) To learn different features of the input data step by step
(v) What is the function of the Rectified Linear Unit (ReLU) layer in a CNN?
(a) To reduce the image size for more efficient processing
(b) To assign importance to various aspects/objects in the input image
(c) To get rid of negative numbers in the feature map and retain positive numbers
(d) To perform the convolution operation on the input image
Answer:
(c) To get rid of negative numbers in the feature map and retain positive numbers
(vi) 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
Question 3.
Answer any 5 out of the given 6 questions (5×1=5)
(i) Which term refers to the correctness and accuracy of data in a dataset?
(a) Data Volume
(b) Data Velocity
(c) Data Veracity
(d) Data Variety
Answer:
(c) Data Veracity
(ii) Which question in the 4 W s Problem Canvas helps identify the people affected by the problem?
(a) What?
(b) Who?
(c) Where?
(d) Why?
Answer:
(b) Who?
(iii) Which computer vision task combines identifying an object and determining its position in the image?
(a) Segmentation
(b) Classification
(c) Classification + Localization
(d) Data Encoding
Answer:
(c) Classification + Localization
(iv) Which of the following is a key reason why deep learning models outperform traditional machine learning models in image and speech recognition tasks?
(a) They use fewer training samples
(b) They rely on manually defined rules
(c) They automatically learn hierarchical features
(d) They avoid the use of neural networks
Answer:
(c) They automatically learn hierarchical features
(v) In a medical diagnosis AI model, it is critical not to miss any actual positive cases of a disease. Which metric should be prioritized?
(a) Precision
(b) Accuracy
(c) Confusion matrix
(d) Recall
Answer:
(d) Recall
(vi) A team is developing an AI chatbot to help users express feelings through text and get suggestions. What technology enables this interaction?
(a) Machine Vision
(b) Expert Systems
(c) Natural Language Processing
(d) Robotics
Answer:
(c) Natural Language Processing
Question 4.
Answer any 5 out of the given 6 questions. (5×1=5)
(i) What is the purpose of using the 4Ws Problem Canvas in the AI project cycle?
(a) To select a random dataset
(b) To define goals of sustainable development
(c) To break down and understand the problem thoroughly
(d) To choose a machine learning algorithm
Answer:
(c) To break down and understand the problem thoroughly
(ii) Statement 1 Accuracy works well even when the dataset is highly imbalanced.
Statement 2 Precision is useful when false positives have a high cost and must be minimized.
(a) Both statements are true
(b) Both statements are false
(c) Statement 1 is true, Statement 2 is false
(d) Statement 1 is false, Statement 2 is true
Answer:
(d) Statement 1 is false, Statement 2 is true
(iii) Which domain of AI is mainly used in the task shown in the image?
(a) Data Analysis
(b) Computer Vision
(c) Robotics
(d) Natural Language Processing
Answer:
(d) Natural Language Processing
(iv) What do you call the data used to train an AI model to make predictions?”
(a) Live Data
(b) Testing Data
(c) Backup Data
(d) Training Data
Answer:
(d) Training Data
(v) A company wants to organize thousands of product images into similar groups without any prior labels. Which learning technique is most suitable?
(a) Supervised Learning
(b) Reinforcement Learning
(c) Unsupervised Learning
(d) Semi-supervised Learning
Answer:
(c) Unsupervised Learning
(vi) What does OpenCV primarily help with in computer vision?
(a) Editing audio files
(b) Designing 3D objects
(c) Performing image and video processing tasks
(d) Creating virtual reality simulations
Answer:
(c) Performing image and video processing tasks
Question 5.
Answer any 5 out of the given 6 questions (5×1=5)
(i) Which AI domain is most likely responsible for enabling a smart assistant to understand and respond to spoken commands?
(a) Computer Vision
(b) Statistical Data
(c) Natural Language Processing
(d) Deep Learning
Answer:
(c) Natural Language Processing
(ii) When evaluating a model for disease detection, which metric is crucial to reduce the risk of missing actual cases?
(a) Precision
(b) Accuracy
(c) Recall
(d) F1 Score
Answer:
(c) Recall
Note
- Recall focuses on catching all actual positive cases.
- High recall minimizes false negatives (missed real cases).
- Critical in medical diagnosis to avoid undetected diseases.
(iii) What is the main function of the ReLU (Rectified Linear Unit) layer in CNN?
(a) To reduce the image resolution
(b) To store classification output
(c) To introduce non-linearity and remove negative values
(d) To blur the image
Answer:
(c) To introduce non-linearity and remove negative values
(iv) Statement 1 Text normalization involves preparing raw text for processing by performing tasks such as tokenization, lemmatization, and punctuation removal.
Statement 2 Document summarization is also considered a standard step in the text normalization process.
(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.
(v) A supermarket uses AI to sort products into “Fruits” or “Grocery”. What type of problem is this?
(a) Regression
(b) Classification
(c) Clustering
(d) Association
Answer:
(b) Classification
(vi) In the context of text processing, what is the purpose of tokenisation?
(a) To convert text into numerical data
(b) To segment sentences into smaller units
(c) To translate text into multiple languages
(d) To summarize documents for analysis
Answer:
(b) To segment sentences into smaller units
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.
A project manager often struggles to meet deadlines due to frequent interruptions.
What are the steps in effective time management they should take?
Answer:
The project manager should prioritize tasks, set clear deadlines, and create a daily schedule. They should also minimize interruptions by setting specific times for checking emails and meetings, thus improving focus and efficiency in meeting deadlines.
Question 7.
What do prepositions show in a sentence? Give an example.
Answer:
Prepositions show relationships between nouns (or pronouns) and other words, often indicating location, time, direction, or manner.
For example, in “The book is on the table,” “on” reveals the book’s position relative to the table, helping to clarify where the book is placed.
Question 8.
What is the role of SDG 10 and SDG 11?
Answer:
SDG 10 aims to reduce inequality within and among countries. It focuses on ensuring equitable income distribution and providing equal opportunities, thus fostering social, economic, and political inclusion. SDG 11 seeks to make cities and human settlements inclusive, safe, resilient, and sustainable by improving urban planning, housing, and environmental management.
Question 9.
What is the main difference between Graphical User Interface (GUI) and Command User Interface (CUI)?
Answer:
The main difference between GUI and CUI is that GUI uses visual elements like windows, icons, and buttons, making it user-friendly and intuitive. In contrast, CUI relies on text commands and is more suitable for users who are comfortable with command-line operations. GUI is generally easier for beginners, while CUI offers more control and flexibility for advanced users.
Question 10.
Sarita, a skilled artisan, started her own jewellery business but struggled to gain initial traction. With the support of a women’s entrepreneurship program, she received mentoring and access to a network of investors. How did this support impact her business?
Answer:
The support from the women’s entrepreneurship program helped Sarita gain valuable mentorship and connect with investors, leading to increased visibility and financial backing for her jewellery business. This support significantly improved her business prospects and growth potential.
Answer any 4 out of the given 6 questions in 20-30 words each.
Question 11.
Why is it important to remove special characters from text data during pre-processing?
Answer:
Removing special characters is crucial in text pre-processing to ensure that the data is clean and consistent.
Special characters can introduce noise and inconsistencies that may hinder the performance of natural language processing models. By normalizing the text, you help improve the quality of the data, making it easier for algorithms to analyze and process.
Question 12.
What type of data does a classification model work with in supervised learning?
Answer:
A classification model in supervised learning works with discrete data. It assigns predefined labels to inputs by analyzing features and categorizing them into distinct classes or groups.
Question 13.
How does a model identify whether an object in a picture is a cat or dog?
Answer:
Deep learning models like CNNs analyze features in an image to identify and label objects such as cats or dogs through a process called object classification.
Question 14.
Which AI field helps machines understand visuals like humans do using data from images and videos?
Answer:
Computer Vision enables machines to interpret and analyze visual inputs such as images and videos,allowing them to see, observe, and understand the world like humans.
Question 15.
What is the basic representation of an image in digital format?
Answer:
In digital format, an image is represented as a matrix of pixel values. Each pixel’s value corresponds to its intensity or colour, with grayscale images having single intensity values per pixel and colour images using multiple channels (e.g., RGB) to represent different colour components.
Question 16.
Why is mapping predictions to reality important in model evaluation?
Answer:
Mapping predictions to reality is crucial because it helps assess how well a model’s predictions match actual outcomes. This evaluation enables the identification of errors such as false positives and false negatives, which informs adjustments to improve model performance. Accurate mapping ensures that the model provides meaningful and actionable insights.
Answer any 3 out of the given 5 questions in 50-80 words each. (3×4=12)
Question 17.
How can the simple act of shopping at a supermarket be related to the concept of classification in artificial intelligence?
Answer:
When you visit a supermarket and use two trolleys-one for fruits and vegetables and the other for groceries-you are performing classification. Similarly, in AI, classification is the process of sorting data into categories. Just like separating perishable items from packaged ones, an AI model learns to differentiate between categories such as spam and non-spam emails, or diseased and healthy patients. The model uses input data to assign a specific class label to each item. This real-life example simplifies the abstract concept of classification, helping learners understand how machines can categorize data using trained algorithms.
Question 18.
In what ways does the 4 Ws Problem Canvas contribute to better understanding and solving a real-world issue in an AI project?
Answer:
The 4Ws Problem Canvas is a strategic tool used during the Problem Scoping stage of the AI project cycle. It enhances clarity by breaking down the problem into four key components: Who, What, Where, and Why. This approach helps identify the stakeholders affected (Who), define the problem and gather supporting evidence (What), pinpoint the context or location of the problem (Where), and understand the expected impact of the solution (Why). By answering these questions, developers can transform a vague challenge into a well-defined, solvable problem, forming a solid foundation for the remaining stages of the AI project cycle.
Question 19.
What is a regression model used for in machine learning?
Answer:
A regression model in machine learning is used to predict a continuous numerical outcome based on input features. It identifies the relationship between dependent and independent variables by fitting a line or curve to the data points. Regression models are commonly used for tasks such as forecasting sales, estimating prices, or predicting trends. They help in understanding how changes in input variables influence the target variable, making them essential for decision-making and analysis.
Question 20.
What are some common techniques for acquiring data for machine learning projects?
Answer:
Common data acquisition techniques include web scraping, using APIs, conducting surveys, and leveraging existing datasets from public or proprietary sources. Web scraping involves extracting data from websites, APIs provide structured data access, surveys collect primary data directly, and existing datasets offer pre-collected, often labelled data suitable for training models.
Question 21.
You are working as a data scientist for a healthcare company that has developed a new diagnostic tool for detecting a particular type of cancer. The diagnostic tool is evaluated using a dataset of 200 patient records. Each record is labelled as either “Cancer Present” or “Cancer Absent,” and the tool’s predictions are compared against the actual diagnoses.
After running the diagnostic tool on the dataset, you obtain the following confusion matrix:
| Predicted Positive | Predicted Negetive | |
| Actual Positive | 50 | 10 |
| Actual Negative | 5 | 100 |
(a) Calculate the accuracy of the diagnostic tool.
(b) Calculate the recall of the diagnostic tool.
Answer:
Confusion Matrix Details:
- True Positives (TP) 50 (Patients correctly identified as having cancer)
- False Negatives (FN) 10 (Patients incorrectly identified as not having cancer)
- False Positives (FP) 5 (Patients incorrectly identified as having cancer)
- True Negatives (TN) 100 (Patients correctly identified as not having cancer)
