Chapter 2: Advanced Concepts of Modeling in AI

Important questions — the ones the board asked most (9)

1. Q1Short answer4 marksAsked: 2026

   (A) Write the full form of CNN and ANN and define them. (B) In the given diagram of a Neural network, identify the layer that should be shown in Box 1 and Box 2 :

   

   Medha Ma’am

   AskMedha’s AI teacher

   Hear it from Medha Ma’am · 120 s

   Model answer · CNN, ANN, Neural Network layers

   1. 1.The full form of CNN is 'Convolutional Neural Network'. Convolutional Neural Network is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image and be able to differentiate one from the other. It is primarily used for image processing.1 mark
   2. 2.The full form of ANN is 'Artificial Neural Network'. Artificial Neural networks are modelled on the human brain and nervous system. They are able to automatically extract features without input from the programmer and are useful when solving problems for which the data set is very large. ANN and CNN are the two types of Deep Learning models.1 mark
   3. 3.The 'Hidden Layer' should be represented in Box 1. In a neural network diagram, the first layer is the Input Layer whose job is to acquire data and feed it to the Neural Network, with no processing occurring at this layer. The layer that comes next, shown in Box 1, is the Hidden Layer, which is the layer in which the whole processing occurs. Each node of the Hidden Layer has its own machine learning algorithm which it executes on the data received from the Input Layer, performing computation using weights and biases on each node.1 mark
   4. 4.The 'Output Layer' should be represented in Box 2. After the Input Layer and the Hidden Layer have processed the data, the last hidden layer passes the final processed data to the Output Layer, shown in Box 2, which then gives it to the user as the final output. Similar to the Input Layer, the Output Layer too does not process the data which it acquires; it is meant for user-interface.1 mark

   Diagram: Draw a neural network with an Input Layer of nodes on the left feeding into Box 1 labelled 'Hidden Layer' with its own nodes, which then feeds into Box 2 labelled 'Output Layer' producing the final output.

   • Write 'Convolutional Neural Network' and 'Image processing' together when giving the full form of CNN.
   • Write 'Artificial Neural Network' and mention 'human brain' when defining ANN.
   • Clearly write 'Hidden Layer' for Box 1 and 'Output Layer' for Box 2, naming the 'Input Layer' as the layer before Box 1.

   Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme

2. Q2Short answer4 marksAsked: 2025

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

   

   Medha Ma’am

   AskMedha’s AI teacher

   Hear it from Medha Ma’am · 80 s

   Model answer · Supervised Learning, working

   1. 1.The diagram represents the concept of Supervised Learning, which is a type of machine learning in which a system of organized machine learning algorithms is trained to perform certain tasks.1 mark
   2. 2.In Supervised Learning, the model is trained using labelled data. Labelled data means that every input given to the model is tagged with its correct, desired output, so the model knows beforehand what answer it should learn to produce for each given input.1 mark
   3. 3.During training, the algorithm learns the relationship between input data and its corresponding output. By going through the labelled data again and again, the algorithm understands the pattern or relationship that connects a given input to its correct output, and this is how the model learns from the input data.1 mark
   4. 4.Finally, the trained model is capable of making accurate predictions on new and unseen data. Once the model has learned the relationship between input and output from the labelled data, it can be given new data, which it has never seen before, and it uses what it has learned to give the correct output as a prediction.1 mark

   Diagram: Draw a flow diagram with boxes: "Labelled Data (Input + Output)" → "Supervised Learning Model (training)" → "Trained Model" → "New/Unseen Data (Input)" → "Prediction (Output)", with arrows showing the direction of flow between each box.

   • Write the words 'Supervised Learning' clearly at the start of your answer.
   • Make sure to write 'labelled data' when describing how the model is trained.
   • Use the words 'relationship between input and output' and 'predictions on new and unseen data' in your explanation.

   Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme

3. Q3Long answer4 marksAsked: 2024

   17. What are Neural networks ? Briefly explain all the layers of a neural network.

   

   Medha Ma’am

   AskMedha’s AI teacher

   Hear it from Medha Ma’am · 105 s

   Model answer · neural networks, layers

   1. 1.Neural networks are a system of organizing machine learning algorithms to perform certain tasks and are loosely modelled after how neurons in the human brain behave. They are a part of Artificial Intelligence, inspired by the structure and function of the human brain, and are able to extract data features automatically without needing the input of the programmer.1 mark
   2. 2.The input layer is the first layer of a Neural Network. The job of the input layer is to acquire data and feed it to the Neural Network for further processing. No processing occurs at the input layer; it simply accepts the raw data into the network and passes it on.1 mark
   3. 3.The hidden layer is located between the input layer and the output layer, and this is where the whole processing occurs. Their name means that these layers are hidden and are not visible to the user. The hidden layer performs computation by means of weights and biases, and information passes from one layer to the other after the value found from this calculation is passed through a selected activation function. There can be multiple hidden layers depending upon the complexity of the function for which the network has been configured.1 mark
   4. 4.The output layer is the final layer of the Neural Network which gives the final output to the user. The last hidden layer passes the final processed data to the output layer, which then gives it to the user as the final result or decision. Similar to the input layer, the output layer too does not process the data which it acquires; it is meant for user-interface.1 mark

   Diagram: Draw a neural network diagram with an Input Layer of nodes on the left, two or more columns of Hidden Layer nodes in the middle, and an Output Layer node on the right, with arrows connecting nodes of each layer to the next, labelled "Input Layer", "Hidden Layer", and "Output Layer".

   • Begin by writing that neural networks are inspired by the human brain and are a system of organizing machine learning algorithms.
   • For the input layer write 'No processing occurs' and that it just acquires and feeds data.
   • For the hidden layer mention 'weights and biases' and that it is where 'the whole processing occurs'; for the output layer state it gives the 'final output' and does not process data.

   Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme

4. Q4Long answer4 marksAsked: 2024

   20. Consider the following graphs (Figure 1 and Figure 2) that demonstrate the two types of Supervised Learning Models of Artificial Intelligence. Identify and explain each model giving suitable examples of each.

   How the model answer begins

   1. The graph showing a scatter of data points with a continuous line fitted through them represents the Regression model, where the output is a continuous numerical value. Regression models work on continuous data and…

   The full answer from Medha Ma’am →
5. Q5Very short answer2 marksAsked: 2026

   Give any two characteristics of a Classification Model.

   How the model answer begins

   1. A Classification model uses predefined classes in which objects are assigned, that is, the data is classified according to the labels to categorize data into predefined categories or classes. For example, in the grading…

   The full answer from Medha Ma’am →
6. Q6Very short answer2 marksAsked: 2026

   Give two differences between Supervised and Unsupervised learning.

   How the model answer begins

   1. Supervised learning uses labelled data, whereas unsupervised learning uses unlabelled data.

   The full answer from Medha Ma’am →
7. Q7Short answer2 marksAsked: 2024

   11. Differentiate between Machine Learning (ML) and Deep Learning (DL).

   How the model answer begins

   1. Machine Learning, or ML, enables machines to improve at tasks with experience. The machine learns from its mistakes and takes them into consideration in the next execution; it improvises itself using its own…

   The full answer from Medha Ma’am →
8. Q8Short answer2 marksAsked: 2024

   14. For a healthcare organisation's objective of predicting disease outbreaks and efficiently allocating resources through the analysis of medical records, would you recommend using supervised learning or unsupervised learning as the preferred machine learning approach ? Explain your choice briefly.

   How the model answer begins

   1. Supervised learning is the most suitable approach for the healthcare organisation's objective of predicting disease outbreaks and efficiently allocating resources through the analysis of medical records.

   The full answer from Medha Ma’am →
9. Q9Short answer2 marksAsked: 2023

   What is Dimensionality Reduction ?

   How the model answer begins

   1. Dimensionality reduction is the process of reducing the number of features or input variables in a dataset.

   The full answer from Medha Ma’am →

Objective questions with the board’s key (1)

1. 1. CBSE 2025

   Which form of learning-based approach does the following diagram indicate ?

   • (A) Clustering
   • (B) Classification ✓
   • (C) Regression
   • (D) Dimensionally Reduction

   Answer: (B)

Questions parents and students ask

How many marks does "Advanced Concepts of Modeling in AI" carry in CBSE Class 10 Artificial Intelligence?

In the CBSE papers of 2023–2026, this chapter carried about 4 marks and about 2 questions a year; by marks it ranks 4 in Artificial Intelligence.

Which are the most important (VVI) questions of "Advanced Concepts of Modeling in AI"?

The 9 questions above are from the board’s real papers, each with the years it was asked; the most-asked come first with their full model answers. All 9 written questions of this chapter, with answers, are in the AskMedha app.

Do the answers follow the board’s marking scheme?

Yes. CBSE publishes its marking schemes; every model answer here is written point by point to the marks the board’s own scheme gives, and checked by a second, independent model.