Machine Learning (ML) is a branch of artificial intelligence where computers learn from data instead of being explicitly programmed with rules.
Rather than telling a system exactly how to solve a problem, you give it examples—and it figures out the patterns on its own.
The core idea
Data → learning → predictions or decisions
The model improves as it sees more data or better examples.
Simple example
- Traditional programming:
Write rules to detect spam (keywords, sender rules, etc.) - Machine learning:
Show the system thousands of emails labeled “spam” or “not spam,” and it learns how to tell the difference.
Main types of Machine Learning
- Supervised learning
Learns from labeled data
Examples: spam detection, price prediction, medical diagnosis - Unsupervised learning
Finds patterns in unlabeled data
Examples: customer clustering, anomaly detection - Reinforcement learning
Learns by trial and error using rewards and penalties
Examples: game-playing AI, robotics, recommendation tuning
Common ML techniques
- Linear and logistic regression
- Decision trees and random forests
- Support vector machines
- Neural networks and deep learning
What Machine Learning is good at
- Recognizing patterns humans can’t easily spot
- Scaling decisions across massive datasets
- Improving performance over time
What it’s not
- It doesn’t “understand” concepts like a human
- It depends heavily on data quality
- It can reflect biases present in the data
How it fits into the AI landscape
- Artificial Intelligence: the broad goal of intelligent behavior
- Machine Learning: a way to achieve AI using data-driven learning
- Generative AI: often built using deep learning models
- Predictive / analytical AI: commonly powered by ML models
