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

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

Chapter 3 - Evaluating Models

Chapter 4 - Statistical Data

Chapter 5 - Computer Vision

Chapter 6 - Natural Language Processing

Chapter 7 - Advance Python

#What is Artificial Intelligence, Machine Learning, and Deep Learning?

1. Artificial Intelligence (AI)

Definition: AI is a broad field of computer science that focuses on creating systems that can perform tasks that normally require human intelligence.
Goal: To make machines think, learn, and make decisions like humans.
Examples:
- Virtual assistants like Siri, Alexa, or Google Assistant
- Self-driving cars
- Spam filters in email

🔑 Think of AI as the “big umbrella” covering everything that makes machines intelligent.

2. Machine Learning (ML)

Definition: ML is a subset of AI that allows machines to learn from data and improve their performance without being explicitly programmed.
Goal: To enable systems to recognize patterns and make predictions.
How it works: Feed the machine with data → machine learns patterns → uses those patterns to make predictions or decisions.
Examples:
- Netflix or YouTube recommendations
- Predicting house prices
- Detecting fraud in banking

🔑 Think of ML as a way for AI to "learn by itself" using data.

3. Deep Learning (DL)

Definition: DL is a subset of ML that uses artificial neural networks (inspired by the human brain) with many layers (“deep” layers).
Goal: To solve very complex problems like image recognition, natural language understanding, and speech recognition.
How it works: Data passes through multiple layers of a neural network, each layer extracts higher-level features, leading to highly accurate predictions.
Examples:
- Facial recognition (like Facebook tagging photos automatically)
- Voice assistants understanding speech
- Medical image diagnosis (like detecting tumors in X-rays)

🔑 Think of DL as the “brain-like” part of ML that handles very complex data like images, speech, and text.

📌 Hierarchy Relationship

AI → The big field (machines acting smart).
ML → A part of AI (machines learning from data).
DL → A part of ML (using neural networks for advanced learning).

#What are the five applications of Machine Learning?

1. Healthcare

Disease prediction and diagnosis
Medical image analysis (X-rays, MRI, CT scans)
Drug discovery and personalized treatment

2. Finance

Fraud detection in banking transactions
Credit scoring and risk assessment
Stock market predictions and algorithmic trading
Application of ML

3. Retail & E-commerce

Product recommendation systems (Amazon, Flipkart, Netflix)
Customer behavior prediction
Dynamic pricing and inventory management

4. Transportation

Self-driving cars (object detection, lane detection, decision-making)
Traffic prediction and route optimization (Google Maps)
Predictive maintenance in vehicles

5. Natural Language Processing (NLP)

Chatbots and virtual assistants (Siri, Alexa, ChatGPT)
Sentiment analysis (social media monitoring)
Language translation (Google Translate)

🔑 In short: Machine Learning is applied in Healthcare, Finance, Retail, Transportation, and NLP-based systems.

#What are the five applications of Deep Learning?

1. Computer Vision

What it does: Helps machines "see" and understand images or videos.
Examples:
- Facial recognition (phone unlock, security cameras)
- Medical imaging (detecting tumors in X-rays, MRIs)
- Object detection in self-driving cars (pedestrians, signals, other vehicles)

2. Natural Language Processing (NLP)

What it does: Enables computers to understand and generate human language.
Examples:
- Virtual assistants (Siri, Alexa, ChatGPT)
- Language translation (Google Translate)
- Sentiment analysis (social media monitoring)
  
  Application of DL

3. Speech Recognition

What it does: Converts spoken language into text or interprets it.
Examples:
- Voice typing on smartphones
- Automatic subtitles in YouTube videos
- Customer support bots handling voice calls

4. Healthcare

What it does: Analyzes complex medical data to assist doctors.
Examples:
- Detecting diseases in medical scans
- Predicting patient health outcomes
- Drug discovery and personalized treatment

5. Autonomous Systems

What it does: Powers systems that can operate with little or no human control.
Examples:
- Self-driving cars (decision-making in real time)
- Drones for delivery and surveillance
- Robotics in manufacturing and surgery

🔑 In short: Deep Learning is widely applied in Computer Vision, NLP, Speech Recognition, Healthcare, and Autonomous Systems.

#What is the difference between ML and DL?

1. Definition

ML (Machine Learning): A subset of AI where algorithms learn from data to make predictions or decisions without being explicitly programmed.
DL (Deep Learning): A subset of ML that uses artificial neural networks with many layers to learn patterns from large and complex data.

2. Data Dependency

ML: Works well even with smaller datasets. Example: predicting house prices from tabular data.
DL: Requires huge amounts of data for good performance. Example: training a self-driving car system.

3. Feature Engineering

ML: Human experts must select or design features (e.g., extracting edges in an image).
DL: Automatically extracts features from raw data (e.g., neural networks learn edges, shapes, objects directly).

4. Computational Power

ML: Can run on normal CPUs, less resource-heavy.
DL: Needs powerful GPUs/TPUs due to large-scale computations.

5. Interpretability

ML: Easier to understand and explain (like decision trees, linear regression).
DL: Harder to interpret (acts like a “black box”), though explainability tools exist.

6. Training Time

ML: Trains faster (seconds to minutes).
DL: Takes longer (hours to weeks) due to complexity and large datasets.

7. Examples

ML: Spam email detection, credit scoring, product recommendations.
DL: Face recognition, speech recognition, self-driving cars, language models like ChatGPT.

📌 In short:

ML is good for simpler, smaller problems where features can be engineered.
DL shines in complex tasks with massive data (like vision, speech, and natural language).

#What is Data? What are the features of Data?

What is Data:

Data is information in any form
For e.g. A table with information about fruits is data
Each row will contain information about different fruits
Each fruit is described by certain features

Fruit ID	Fruit Name	Color	Taste	Price (₹/kg)
1xx	Apple	Red	Sweet	120
2	Banana	Yellow	Sweet	60
3	Orange	Orange	Tangy	80
4	Mango	Yellow	Sweet	150
5	Lemon	Green	Sour	40

Features:

Columns of the tables are called features
In the fruit dataset example, features may be name, color, taste, price etc.
Some features are special, they are called labels

#What is labeled and unlabeled data?

1. Labeled Data

Definition: Data that already has input + output (labels) provided.
It tells the machine not only the raw information but also the correct answer.
Used in Supervised Learning.

✅ Example:
A dataset for fruit classification:

Fruit Image	Label (Fruit Name)
🍎 (image)	Apple
🍌 (image)	Banana
🍊 (image)	Orange

Here, each image (input) is tagged with the correct label (output).

Uses:

Spam detection (emails labeled as spam/not spam)
Disease diagnosis (X-rays labeled as "normal" or "tumor")
Facial recognition (faces labeled with names)

2. Unlabeled Data

Definition: Data that has only input but no output labels.
The machine only sees the raw data and must find patterns by itself.
Used in Unsupervised Learning.

✅ Example:
A dataset of fruit images without names:

Fruit Image
🍎 (image)
🍌 (image)
🍊 (image)

The machine doesn’t know what each fruit is called, but it can group them by similarity (clustering).

Uses:

Customer segmentation (grouping buyers by behavior without labels)
Market basket analysis (finding product patterns in shopping carts)
Document/topic clustering

📌 Key Difference

Labeled Data = Input + Output (answer given) → Used in Supervised Learning
Unlabeled Data = Input only (no answer) → Used in Unsupervised Learning