Machine Learning
Introduction
What is Machine Learning?
• Machine Learning (ML) is a branch of Artificial
Intelligence (AI).
• It allows computers to learn from data and
make predictions or decisions.
• No need for explicit programming for every
rule.
Simple Definition
• Machine Learning = Data + Algorithms →
Learning → Predictions
• Example:
• A spam filter learns to classify emails as spam
or not spam based on examples.
Real-World Examples
• Gmail spam detection
• Netflix or YouTube recommendations
• Self-driving cars
• Voice assistants (Alexa, Siri)
• Fraud detection in banks
Key Components of ML
• Data – Experience or examples
• Model/Algorithm – Learns from data
• Training – Adjusting model to minimize error
Types of Machine Learning
• Supervised: Learn from labeled data (e.g.,
Predict exam result)
• Unsupervised: Find hidden patterns (e.g.,
Customer segmentation)
• Semi-Supervised: Mix of both (e.g., Speech
recognition)
• Reinforcement: Learn by rewards (e.g., Game
playing, robotics)
Supervised Learning Example
• Predict if a student will pass/fail based on study
hours:
Marks Result
0-39 Fail
40-50 Pass
51-74 FC
75-89 A
90-100 D
• The model learns the relationship between Marks
and Result.
Common ML Algorithms
• Supervised: Linear Regression, Logistic
Regression, Decision Trees
• Unsupervised: K-Means, PCA
• Reinforcement: Q-Learning, Deep Q-Network
Why Machine Learning Matters
• Automates complex tasks
• Learns from experience
• Improves with more data
• Powers modern intelligent systems
Relationship between AI, ML, and DL
• AI ⊃ ML ⊃ Deep Learning
• AI – Broad field of intelligent systems
• ML – Systems that learn from data
• DL – Neural networks that learn deep patterns
Summary
• ML is about learning from data
• Main types: Supervised, Unsupervised,
Reinforcement
• Powers many real-world applications
• Key part of Artificial Intelligence