Notes – ML Introduction
Machine Learning (ML) is a branch of Artificial Intelligence (AI) that allows machines to learn from data and improve their performance without being explicitly programmed.
“Instead of writing rules, we teach machines using examples.”
What is Machine Learning?
Machine Learning uses algorithms that automatically find patterns in data and make predictions or decisions based on those patterns.
For example:
- If you show a machine hundreds of images of cats and dogs, it can learn to tell them apart without being told the rules.
Why is ML Important?
- Automates decision-making
- Improves with experience (more data = better accuracy)
- Powers modern applications like recommendations, chatbots, fraud detection, and self-driving cars
How Does ML Work?
- Collect Data – Examples of past behavior or events
- Train a Model – Use algorithms to find patterns in the data
- Make Predictions – Apply the model to new data
- Improve – With more data, the model keeps getting better
Real-World Examples of ML
| Use Case | Machine Learning at Work |
|---|---|
| Spam detection | |
| E-commerce | Product recommendations |
| Banking | Loan approval, fraud detection |
| Healthcare | Predicting diseases from symptoms |
| Social Media | Personalized feed, face tagging |
Types of Machine Learning
| Type | Description | Example |
|---|---|---|
| Supervised | Learns from labeled data | Predicting house prices from features |
| Unsupervised | Finds hidden patterns in unlabeled data | Customer segmentation from behavior |
| Reinforcement | Learns from rewards and penalties | Game-playing AI like AlphaGo |
ML vs Traditional Programming
| Traditional Programming | Machine Learning |
|---|---|
| Programmer writes rules | Algorithm learns rules from data |
| Input + Logic → Output | Input + Output → Algorithm learns logic |
| Fixed and rigid | Flexible and self-improving |
