AI Glossary Term

What does “Machine Learning (ML)” mean?

Definition

Methods that allow systems to learn patterns from data and improve over time.

Browse the full AI Glossary Explore all free AI guides

How Machine Learning (ML) works

Example

Instead of writing rules for spotting spam, you give a program thousands of emails marked spam or not. It finds the patterns itself and applies them to new emails.

Why it matters

Machine learning underlies most modern AI products, from recommendations to speech recognition. Its results depend on the data it learns from.

Common questions

What are the main types?

Supervised, unsupervised, and reinforcement learning, plus self-supervised learning used for large language models.

Does machine learning need a lot of data?

Usually, though the amount varies, and techniques such as transfer learning reduce the need.

Can a model keep learning after deployment?

Most are fixed until retrained, though some systems update continuously.

Model DriftPerformance degradation over time as real-world conditions diverge from training assumptions.Data DriftA shift in real-world input data over time that can degrade model performance.Unsupervised LearningLearning patterns from unlabeled data without explicit target outputs.Continual LearningTraining approaches that let a model keep learning from new data without forgetting prior knowledge.Data AugmentationTechniques that create modified training examples to improve model generalization.EnsembleCombining predictions from multiple models to improve robustness or accuracy.

Learn more in our free guides

Deep Learning Reinforcement Learning Machine Learning Basics Supervised Learning

Test yourself

Deep Learning Quiz Reinforcement Learning Quiz Machine Learning Basics Quiz