CBSE Class 12 Artificial Intelligence (Code 843) Question Paper for the session 2025–26 is an essential resource for students preparing for their board exams. It provides a clear understanding of the exam pattern, marking scheme, and the types of questions that are frequently asked. By practicing this paper, students can evaluate their preparation level and identify important topics such as AI project cycle, data handling, machine learning concepts, and ethical issues in AI. This helps in building confidence and improving time management during the actual examination.
Along with the question paper, detailed solutions play a crucial role in effective preparation. Step-by-step answers with proper explanations help students understand the correct approach to solving each question. These solutions not only clarify concepts but also highlight common mistakes to avoid. Students can download the PDF for easy access and regular practice, making it a valuable study material to score high marks in the CBSE Class 12 AI (843) board exam.
CBSE Class 12 AI 843 Question Paper 2025-26 with Solution
Exam Date March 24, 2026
Series RSP1Q
Question Paper Code 367 Set 4
ARTIFICIAL INTELLIGENCE (843) - PYQP 2026
(Session 2025-26)
Time allowed : 2 hours
Maximum Marks : 50
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 05 questions.
- Marks allotted are mentioned against each question/part.
- There is no negative marking.
- Do as per the instructions given.
- 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
1. Answer any 4 out of the given 6 questions on Employability Skills. (4x1=4)
(i) A statement which conveys the exact message that you are trying to convey to the other person is called __________ statement.
a) Clear
b) Concise
c) Accurate
d) Active
(ii) Which of the following is NOT related to positive attitude?
a) It makes a person happier
b) Helps to build and maintain relationships
c) Decreases one’s chances of success
d) Helps to make better decisions
(iii) How does the intrinsic motivation occur?
Ans: Intrinsic motivation comes from internal interest, enjoyment, and personal satisfaction.
(iv) ________ are like new pages, which are added to separate different topics in a presentation.
a) Text
b) Document
c) File
d) Slides
(v) Which of the following is NOT a characteristic of entrepreneurship?
a) It is a non-economic activity
b) It deals with optimisation in utilisation of resources
c) Ability to take risks
d) Identifying an opportunity
(vi) Write the expanded form of FIGs.
Ans: Farmer Interest Groups
2. Answer any 5 out of the given 6 questions. (5x1=5)
(i) A retail company notices a sudden decline in online sales during the last quarter. The data analytics team decides to investigate the underlying causes of this drop. They begin examining customer behaviour patterns, website traffic, and product return rates to identify factors contributing to the decline. Which type of data analytics is the team primarily using?
a) Descriptive Analytics
b) Diagnostic Analytics
c) Predictive Analytics
d) Prescriptive Analytics
(ii) When a computer processes an image, it perceives it as a collection of tiny squares. What are these tiny squares called?
a) Vectors
b) Pixels
c) Kernels
d) Neurons
(iii) A social media analyst is working with a large collection of audio files, images, and video files to study user engagement and content trends on various platforms. Which type of Big Data is the analyst dealing with?
a) Structured Data
b) Semi-Structured Data
c) Unstructured Data
d) Filter Data
(iv) Which component of a neural network decides whether a neuron should be activated or not based on the input it receives?
a) Activation Function
b) Bias
c) Weight
d) Neuron
(v) What is the primary objective of Generative AI?
a) To classify existing data into different categories
b) To define class boundaries within existing data for classification tasks
c) To generate new data that resembles its training samples
d) To delete redundant data from large datasets
(vi) Which ethical consideration in Data Storytelling specifically addresses the need to "Clearly cite the sources of the data, methods used for analysis, and any limitations or biases"?
a) Accuracy
b) Transparency
c) Respect for Privacy
d) Story Relevance
3. Answer any 5 out of the given 6 questions. (5x1=5)
(i) The primary purpose of Prescriptive Analytics is to:
a) Uncover root causes and factors contributing to specific outcomes
b) Identify patterns, trends, and anomalies in past data
c) Forecast future events or behaviours
d) Recommend specific actions or interventions based on predictive insights
(ii) A bank’s fraud detection team analyses thousands of daily transactions to identify suspicious activities. During the analysis, they look for unusual spending patterns or transactions that significantly differ from a customer’s normal behaviour. This process of finding such irregular or abnormal trends within a dataset is associated with:
a) Clustering
b) Recommendation
c) Regression
d) Anomaly Detection
(iii) A wildlife research organization is building a computer vision system to monitor animal movements in forests. They install motion-sensing cameras that automatically capture photos and videos of animals in their natural habitat for further analysis. The organization is currently working on which stage of the computer vision process?
a) Image Acquisition
b) Preprocessing
c) Feature Extraction
d) Detection and Segmentation
(iv) A healthcare analytics firm gathers patient information from a large number of hospitals, laboratories, and wearable devices. Before analysing this Big Data, the company ensures the consistency, accuracy, quality, and trustworthiness of the data to produce reliable insights and reports. Which Big Data characteristic is illustrated in this scenario?
a) Volume
b) Velocity
c) Variety
d) Veracity
(v) In context of Neural Networks, the process in which input data flows through the layers, activations are computed, and the predicted output is compared to the actual target is specifically known as ________.
a) Back Propagation
b) Deep Learning
c) Forward Propagation
d) Optimization
(vi) Which data visualization type provides a visual representation of word data where word size indicates frequency and importance?
a) Scatter Plot
b) Word Cloud
c) Line Graph
d) Bar Chart
4. Answer any 5 out of the given 6 questions. (5x1=5)
(i) What is the main purpose of evaluation in an AI project cycle?
a) To collect data for training the model
b) To assess how well a model performs after training
c) To deploy the model into real-world systems
d) To visualize the data used for model building
(ii) A security company is designing a computer vision system for night surveillance. The captured footage often contains random dots and blurry patches due to low lighting. To make the images clearer before object detection, the system applies a technique to remove these blurry patches and distortions. Which technique of Computer Vision process is being used by the system?
a) Cropping image
b) Noise Reduction
c) Resizing image
d) Image Normalization
(iii) Which type of processing used in Big Data Analytics handles small batches of data at a time to minimize the delay between data collection and analysis, enabling quicker decision-making?
a) Batch processing
b) Stream processing
c) Predictive analysis
d) Descriptive analysis
(iv) Alpha Innovations is a company specializing in artificial intelligence solutions. For a project, the development team of the company decides to use a type of neural network that extracts features from images and incorporates a three-dimensional arrangement, making it effective for processing visual data. Identify the type of neural network.
a) Recurrent Neural Network
b) Feed Forward Neural Network
c) Standard Neural Network
d) Convolutional Neural Network
(v) What is an Artificial Neural Network (ANN) with two or more hidden layers known as?
a) A Basic Neural Network
b) A Deep Neural Network
c) A Perceptron
d) A Connection Neural Network
(vi) Variational Autoencoders (VAEs) are computer programs designed to learn from data in a unique way. What are their two main parts?
a) A generator and a discriminator
b) An encoder and a decoder
c) A Large Language Model and a Transformer
d) A recurrent and a convolutional network
5. Answer any 5 out of the given 6 questions. (5x1=5)
(i) Assertion (A): Social media posts and images are examples of structured data.
Reason (R): Unstructured data does not follow a predefined format.
a) Both (A) and (R) are true, and (R) is the correct explanation of (A)
b) Both (A) and (R) are true, but (R) is not the correct explanation of (A)
c) (A) is false, but (R) is true
d) Both (A) and (R) are false
(ii) The resolution of a digital image is determined by which factor?
a) The numerical value assigned to each pixel (0 to 255)
b) The number of pixels in the image
c) The size of the file in bytes
d) The time taken for image acquisition
(iii) A company is developing a smart security camera. The camera analyses each frame to automatically identify people, vehicles, and other objects. It marks each detected object by drawing bounding boxes around them. This activity of identifying and locating multiple objects of interest within the image by drawing bounding boxes is called:
a) Semantic Segmentation
b) Instance Segmentation
c) Object Detection
d) Histogram Equalization
(iv) Innovative Labs, a startup focused on developing intelligent language models, is training a neural network to improve its text prediction accuracy. During the training process, the team uses the practice of fine-tuning the weights of the neural network based on the error rate (loss) obtained in the previous iteration to minimize error. This practice is known as ________.
a) Forward Propagation
b) Activation Function
c) Back Propagation
d) Deep Learning
(v) Why are Large Language Models (LLMs) referred to as 'large'?
a) They use a large number of GPUs.
b) They are trained on massive datasets of text and code.
c) They can only generate long text outputs.
d) They have more layers than other models.
(vi) The key element ‘Visuals’ in data storytelling serves the purpose of:
a) Providing the basic facts or raw facts about an entity.
b) Organizing the key information in a linear and coherent fashion.
c) Representing data pictorially to convey complex information clearly and effectively.
d) Establishing the setting and introducing main characters of the data story.
SECTION B: Subjective Type Questions
Answer any 3 out of the given 5 questions on Employability Skills. (3x2=6)
Answer each question in 20-30 words:
6. List out the problems faced by the person who lacks in communication skills.
Ans: Here are some problems faced by a person who lacks communication skills:
(i) Difficulty in expressing thoughts and ideas clearly
(ii) Misunderstandings in personal and professional life
(iii) Lack of confidence while speaking
(iv) Poor relationships with others
(v) Limited career growth opportunities
(vi) Difficulty in teamwork and collaboration
7. State any four techniques how a person can become result-oriented.
Ans: (i) Set clear and specific goals
(ii) Plan and prioritize tasks properly
(iii) Stay focused and avoid distractions
(iv) Manage time effectively
(v) Monitor progress regularly
(vi) Stay positive and motivated towards achieving results
8. Give any four advantages of Presentation software.
Ans: (i) Helps present information in a clear and organized way
(ii) Makes content more attractive using images, videos, and animations
(iii) Easy to edit, update, and reuse slides
(iv) Saves time with ready-made templates and designs
(v) Improves audience understanding and engagement
(vi) Allows easy sharing and delivery of presentations
9. Who are called Business Entrepreneurs?
Ans: Business entrepreneurs are individuals who start and run a business by organizing resources, taking risks, and making decisions with the aim of earning profit.
10. Explain the role of green-jobs in eco-tourism.
Ans: Green jobs in eco-tourism help protect the environment while creating local employment. They support activities like conservation, waste management, and eco-friendly practices, making tourism sustainable and beneficial for both nature and the community.
Answer any 4 out of the given 6 questions in 20-30 words each. (4x2=8)
11. Name any four evaluation Metrics for Classification.
Ans: (i) Accuracy (ii) Precision (iii) Recall (iv) F1-Score
12. What is the role of preprocessing images in the computer vision process? How is it different from High Level Processing?
Ans: Image preprocessing is used to improve the quality of images before analysis. It includes steps like noise removal, resizing, normalization, and enhancing contrast. This helps in making the image clearer and more suitable for further processing, leading to better accuracy in results.
Difference from High-Level Processing:
Preprocessing is a low-level task that focuses on improving image quality, while high-level processing deals with understanding and interpreting the image, such as object detection, recognition, and decision-making.
13. Mention any two disadvantages/challenges associated with using Big Data.
Ans: (i) Data privacy and security issues
(ii) High cost of storage and processing
(iii) Difficulty in managing and analyzing large volumes of data
14. What is 'bias' in a neural network? Mention any one of its functions.
Ans: Bias in a neural network is a parameter added to the weighted sum of inputs to help the model adjust the output.
Functions of bias:
(i) Helps shift the activation function (left or right)
(ii) Allows the model to fit data more accurately even when inputs are zero
15. State any two risks associated with Large Language Models (LLMs) that arise from the training process or the training data.
Ans: (i) Bias in training data: If the data contains biases, the model may produce unfair or biased outputs.
(ii) Inaccurate or misleading information: The model may generate incorrect or false information learned from imperfect training data.
16. Define the term Data Storytelling. Mention any one reason why Data Storytelling has become very powerful today.
Ans: Data Storytelling is the process of presenting data using visuals and narrative to communicate insights in a clear and meaningful way.
Reasons why it is powerful today:
(i) Helps people understand complex data easily through visuals and stories
(ii) Supports better decision-making by clearly highlighting key insights
Answer any 3 out of the given 5 questions in 50-80 words each. (3x4=12)
17. With reference to the steps of Data Science Methodology, define the process of 'data collection'. Also differentiate between primary and secondary data sources of data collection with suitable examples.
Ans: Data collection is the process of gathering relevant data from different sources to solve a problem or answer a question. It ensures that accurate and useful data is available for analysis.
Difference between Primary and Secondary Data Sources:
Primary Data: Data collected directly by the researcher for a specific purpose.
Example: Surveys, interviews, observations.
Secondary Data: Data already collected by others and used for analysis.
Example: Government reports, websites, research papers.
18. List and briefly explain the four steps involved in the working process of Big Data Analytics.
Ans: Here are the four steps involved in Big Data Analytics:
(i) Data Collection: Gathering large amounts of data from various sources like sensors, social media, and databases.
(ii) Data Storage: Storing the collected data using technologies like cloud storage or distributed systems.
(iii) Data Processing: Cleaning, organizing, and analyzing data to extract useful information.
(iv) Data Analysis & Visualization: Interpreting the results and presenting them using charts, graphs, or dashboards for decision-making.
19. Describe the structure of an Artificial Neural Network by explaining its three fundamental layers, and define the role of the weights assigned to each connection between the nodes.
Ans: An Artificial Neural Network (ANN) is structured in three main layers:
(i) Input Layer: This layer receives the input data (features) and passes it to the next layer.
(ii) Hidden Layer(s): These layers process the inputs using mathematical operations and activation functions. They help in learning patterns and relationships in the data.
(iii) Output Layer: This layer produces the final result or prediction based on the processed data.
Role of Weights: Weights are values assigned to the connections between nodes. They determine the importance of each input. During training, these weights are adjusted so that the network can make accurate predictions.
20. Differentiate between Generative AI and Discriminative AI based on their Purpose, Training Focus, Application, and Models.
Ans:
| Basis | Generative AI | Discriminative AI |
|---|---|---|
| Purpose | Generates new data similar to existing data | Classifies or predicts labels for given data |
| Training Focus | Learns the underlying data distribution | Learns the boundary between different classes |
| Application | Image generation, text generation, chatbots | Spam detection, image classification, sentiment analysis |
| Models | GANs, VAEs, GPT | Logistic Regression, SVM, Decision Trees |
21. Define the terms 'Data' and 'Data Visualization'. Explain the uses of the 'Heat Map' and 'Candlestick Chart' visualization types.
Ans: Data: Data refers to raw facts, figures, or information collected for analysis.
Data Visualization: Data visualization is the graphical representation of data using charts, graphs, or maps to make information easy to understand.
Uses of Heat Map: A heat map uses colors to represent data values. It helps in identifying patterns, trends, or areas of high and low intensity, such as website clicks or temperature variations.
Uses of Candlestick Chart: A candlestick chart is mainly used in financial markets to show price movements (open, high, low, close) of stocks over time. It helps in analyzing trends and making trading decisions.
Download Now - Class 12 AI 843 Previous Year Question Paper (PYQP) 2025-26 with Solution
