Class 10 AI Chapter - Modelling in AI Topic - AI Model

 

Class 10 Artificial Intelligent Code 417 Solutions

Session 2025-26

Artificial Intelligence code 417 syllabus pdf class 10 solutions. Class 10 AI Book. Class 10 AI Notes. This article provides complete solution for class 10 AI (Artificial Intelligence)  Code - 417 students 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.

--------------------------------------------------

Chapter - Modelling in AI
Other Topics

• AI ML DL
• AI Modelling
• Machine Learning
• Deep Learning 
  

-------------------------------------------------

Data in AI

In simple terms, data refers to raw facts, figures, or information that can be collected, stored, and analyzed. In the context of Artificial Intelligence (AI), data is the foundational input that is used to train models, make predictions, and drive decision-making. Without data, AI systems cannot learn or function effectively.

Types of Data in AI

Data in AI can be classified in several ways depending on structure, source, and labeling. Here's a breakdown:

1. Based on Structure

a. Structured Data

• Definition: Data organized in rows and columns (tabular format).
• Examples: Spreadsheets, databases, financial records.
• Use in AI: Good for traditional machine learning algorithms (e.g., regression, decision trees).

b. Unstructured Data

• Definition: Data that doesn't follow a specific format or structure.
• Examples: Text documents, images, audio files, videos.
• Use in AI: Requires techniques like deep learning, natural language processing (NLP), or computer vision.

c. Semi-Structured Data

• Definition: Partially structured data that doesn't fit neatly into tables but has some organizational properties.
• Examples: JSON, XML, HTML documents.
• Use in AI: Useful for web data extraction, data integration tasks.
  
  

2. Based on Labeling (Supervision)

a. Labeled Data (Annotated Data)

• Definition: Data that comes with tags or labels indicating the correct answer.
• Examples: Images with tags like "cat", "dog"; emails labeled as "spam" or "not spam".
• Use in AI: Used in supervised learning where models learn from example-input/output pairs.

b. Unlabeled Data

• Definition: Raw data with no labels or annotations.
• Examples: Random internet text, untagged photos.
• Use in AI: Used in unsupervised learning (e.g., clustering, dimensional reduction).

c. Partially Labelled Data

• Definition: A mix of labelled and unlabelled data.
• Use in AI: Used in semi-supervised learning where a small labelled set helps guide learning on a large unlabelled set.
  
  

3. Based on Data Modality

a. Text Data

• Examples: Articles, tweets, customer reviews.
• AI Application: Natural Language Processing (e.g., chatbots, sentiment analysis).

b. Image Data

• Examples: Photographs, medical scans.
• AI Application: Computer Vision (e.g., facial recognition, object detection).

c. Audio Data

• Examples: Speech recordings, sound clips.
• AI Application: Speech recognition, emotion detection.

d. Video Data

• Examples: Surveillance footage, video tutorials.
• AI Application: Action recognition, video summarization.

e. Time-Series Data

• Examples: Stock prices, sensor data over time.
• AI Application: Forecasting, anomaly detection.

Summary Table

Type	Format	Used In
Structured	Tables/Spreadsheets	Traditional ML
Unstructured	Images, Text, Audio	Deep Learning, NLP, Computer Vision
Labeled	Tagged Inputs	Supervised Learning
Unlabeled	Raw Data	Unsupervised Learning
Text	Words/Sentences	NLP, Translation
Image	Pixels	Computer Vision
Audio	Sound Waves	Voice Assistants, Music Classification
Time-Series	Sequential Data	Forecasting, IoT Analytics

---

Modeling in AI

Modeling in AI is the process of creating a system that represents or mimics human decision-making, reasoning, or learning. This model uses input data to make predictions or solve problems.

In simple words: It’s like teaching a computer how to think, act, or make decisions by building a digital version (model) of a real-world process.

AI Model

Rule-Based Approach

Definition:

A rule-based approach uses a set of predefined "if-then" rules written by humans to make decisions.

Features:

• Based on human knowledge and logic.
• Rules are manually coded.
• Used for simple, well-defined problems.

Example:

if temperature > 30:
    print("It's hot")

AI doesn't learn here — it only follows rules.

Advantages:

• Easy to understand and explain.
• Good for fixed or small problem domains.

Disadvantages:

• Not suitable for complex or changing environments.
• Difficult to scale.
  
  

Learning-Based Approach

Definition:

A learning-based approach allows the AI to learn patterns and make decisions by analyzing large amounts of data.

Features:

• Based on data and statistical models.
• AI learns from experience.
• Uses algorithms like neural networks, decision trees, etc.

Example:

A spam filter learns to recognize spam emails by analyzing thousands of labeled examples.

The model improves its performance over time by training on more data.

Advantages:

• Can handle complex and dynamic problems.
• Adapts and improves with more data.

Disadvantages:

• Requires large datasets and computing power.
• Harder to explain how decisions are made (black-box).
  
  

Summary Table:

Feature	Rule-Based Approach	Learning-Based Approach
Based On	Human-written rules	Data and algorithms
Learning	No	Yes
Flexibility	Low	High
Example Use Case	Thermostat logic	Face recognition, spam detection
Complexity Handling	Poor	Good

---