Class 10 AI Chapter - Modelling in AI Topic - Question/Answer

 

Class 10 Artificial Intelligent Code 417 Solutions

Session 2025-26

Artificial Intelligence code 417 syllabus pdf class 10 solutions. Class 10 AI Book. Part - A,  Part - B, and Python. This article provides complete solution for class 10 AI (Artificial Intelligence)  Code - 417 solution according to new syllabus 2025 – 26. In this article first of all go through the AI Code - 417 syllabus and then follow chapter wise notes. Class 10 AI MCQs Quiz with answers.

Part A - Employability Skills Question/Answers 

Chapter 1 -Communication Skills - II 

Chapter 2 -Self - Management Skills - II    

Chapter 3 - ICT Skills - II 

Chapter 4 - Entrepreneurial Skills - II 

Chapter 5 - Green Skills - II

Part B - Subject Specific Skills Question/Answers 

Chapter 1 -AI Project Cycle & Ethics 

Chapter 2 - Modelling in AI

• Question Answer - 1
• Question Answer - 2
• Question Answer - 3
• Question Answer - 4

Chapter 3 - Evaluating Models

Chapter 4 - Statistical Data

Chapter 5 - Computer Vision

Chapter 6 - Natural Language Processing

Chapter 7 - Advance Python

#What is supervised learning? 
Explain classification and regression.

Supervised Learning

Supervised learning is a type of machine learning where a model is trained using labeled data.

• Labeled data means each input has a correct output (answer) already provided.
• The model learns the mapping:

$$Input(X)\to Output(Y$$

• After training, the model can predict outputs for new unseen inputs.
  

👉 Example: If we train a model with data of students’ study hours (input) and their exam scores (output), it learns the relationship. Later, it can predict the score for a new student based on their study hours.

Types of Supervised Learning

There are two main types: Classification and Regression.

1. Classification

• Goal: Categorize data into discrete classes (categories).
• Output: A
• Examples:
  
  • Spam Email Detection → (Spam / Not Spam)
  • Disease Diagnosis → (Positive / Negative)
  • Handwritten Digit Recognition → (0–9 classes)

👉 It’s like answering “Which category does this input belong to?”

2. Regression

• Goal: Predict
• Output: A
• Examples:
  
  • Predicting house prices
  • Forecasting stock market values
  • Estimating temperature tomorrow

👉 It’s like answering “How much?” or “What value?”

Key Difference: Classification vs Regression

xxxFeature	Classification	Regression
Output Type	Discrete labels (categories)	Continuous values
Examples	Spam/Not Spam, Disease/No Disease	Price prediction, Temperature
Algorithms	Logistic Regression, Decision Trees, SVM, Neural Networks	Linear Regression, Polynomial Regression, Neural Networks

⚡In short:

• Classification = “Which group?”
• Regression = “What value?”
  
  

#What is unsupervised learning? 
Explain clustering and association.

Unsupervised Learning

Unsupervised learning is a type of machine learning where the model is trained on unlabeled data.

• Unlike supervised learning, there are no predefined outputs.
• The goal is to find hidden patterns, groupings, or structures in the data.
• Useful when labels are expensive or impossible to obtain.

👉 Example: Feeding a dataset of customer purchase histories without telling the model which customers are similar — the algorithm discovers groups (clusters) on its own.

Main Types of Unsupervised Learning

The two most common approaches are Clustering and Association.

1. Clustering

• Definition: Grouping data points into clusters so that items in the same cluster are more similar to each other than to those in other clusters.
• Goal: Discover natural groupings in data.
• Examples:
  
  • Customer segmentation (grouping buyers by behavior)
  • Document/topic grouping (news articles by theme)
  • Image compression (grouping similar pixels)

Evaluation (since labels aren’t given)

• Silhouette score (how well-separated clusters are).
• Davies–Bouldin Index,

2. Association

• Definition: Discovering interesting relationships (associations) between variables in large datasets.
• Goal: Find rules of the form
  $$$$If A, then B\text {If A, then B}
  (also called association rules).
• Examples:
  
  • Market Basket Analysis:
    
    • “If a customer buys bread and butter, they are likely to buy jam.”
  • Recommender systems:
    
    • “Users who watched Movie A also watched Movie B.”

Common Algorithms

• Apriori Algorithm (classic method for frequent itemset mining).
• FP-Growth Algorithm (faster, builds a tree structure to find frequent patterns).

Quick Difference: Clustering vs Association

Feature	Clustering	Association
Goal	Group similar data points	Find rules/relationships between items
Output	Clusters (groups of data)	Association rules (If A → B)
Example	Grouping customers into segments	Finding “people who buy X also buy Y”
Algorithms	K-Means, Hierarchical, DBSCAN	Apriori, FP-Growth

⚡In short:

• Clustering = “Who/what belongs together?”

• Association = “What items go together?”

 

#What is deep learning? 
Explain Artificial Neural Networks(ANN) and Convolutional Neural Networks(CNN).

Deep Learning

Deep Learning is a branch of Artificial Intelligence (AI) and a subset of Machine Learning (ML) that uses algorithms inspired by the structure and function of the human brain, called Artificial Neural Networks (ANNs).

• It automatically learns features from large amounts of data without much manual feature engineering.
• Deep learning models are called "deep" because they consist of many layers of neurons (hidden layers).
• It is widely used in image recognition, natural language processing, speech recognition, self-driving cars, healthcare, and more.

Artificial Neural Networks (ANN)

An Artificial Neural Network is the basic building block of deep learning.
It mimics how the human brain’s neurons pass signals.

Structure of ANN:

1. Input Layer – receives raw data (e.g., image pixels, text, numbers).

2. Hidden Layers – process the input using weights, biases, and activation functions.

3. Output Layer – gives the final result (e.g., classification: cat/dog, prediction: price value).

How ANN works:

• Each neuron gets inputs, multiplies them by weights, adds a bias, and applies an activation function to decide whether to pass the signal forward.

• Through training (using backpropagation and gradient descent), the ANN learns to adjust its weights to reduce errors.

👉 ANN is great for general problems like regression, classification, or pattern recognition.

Convolutional Neural Networks (CNN)

A Convolutional Neural Network is a special type of ANN, mainly designed for image and video data.
It is very powerful for computer vision tasks such as face recognition, medical image analysis, and object detection.

Key Layers in CNN:

1. Convolutional Layer

   • Applies filters (kernels) to scan over the image.

   • Detects local features like edges, corners, textures.

2. Pooling Layer

   • Reduces the size of the feature maps (downsampling).

   • Makes the model faster and reduces overfitting.

3. Fully Connected Layer (Dense Layer)

   • Works like a traditional ANN.

   • Combines features detected earlier to classify the image (e.g., cat 🐱 vs dog 🐶).

Why CNN is powerful:

• It automatically learns important spatial features (shapes, colors, patterns) instead of needing manual feature extraction.

• Much more efficient and accurate than ANN for image-related tasks.

✅ Summary:

• Deep Learning → Subset of ML using neural networks with many layers.

• ANN → Basic type of neural network for general tasks (classification, regression).

• CNN → Specialized ANN for images/videos; uses convolution and pooling to extract spatial features.