What is Machine Learning (ML)?

What is Machine Learning?

Machine learning (ML) is a subset of artificial intelligence in which systems learn patterns from data and improve their performance on a task without being explicitly programmed with rules for that task.

Why It Matters

Machine learning is the engine behind virtually every modern AI application — from recommendation systems on Netflix to fraud detection in banking to the language models powering ChatGPT. Understanding ML is essential because it's the parent discipline of deep learning, large language models, and most techniques discussed in this dictionary.

How It Works

A machine learning system follows a general cycle:

1. Data collection — gather labeled or unlabeled examples.
2. Feature extraction — identify measurable properties in the data (or let the model learn them automatically in deep learning).
3. Model training — an algorithm adjusts internal parameters to minimize error on the training data.
4. Evaluation — test the model on unseen data to measure performance.
5. Deployment — serve the model to make predictions on new inputs (inference).

ML approaches fall into three main paradigms:

• Supervised learning — learn from labeled examples (input → known output).
• Unsupervised learning — discover structure in unlabeled data.
• Reinforcement learning — learn by trial and error with a reward signal.

Example

An email spam filter is a classic ML application. The system is trained on thousands of emails labeled "spam" or "not spam." It learns patterns (certain words, sender patterns, link structures) and can then classify new incoming emails automatically — without a programmer writing rules for every type of spam.