AI glossary Models & Architecture
What is machine learning (ML)?
Machine Learning (ML)
← All glossary termsA branch of AI in which systems learn patterns from data to make predictions or decisions, instead of following rules written by hand.
Explained
Machine learning (ML) is the part of artificial intelligence in which a system improves at a task by learning from examples rather than from explicit programming. A model is trained on data, adjusts its internal parameters to reduce its errors, and is then used to predict or classify new cases: whether a transaction is fraud, how much demand to expect, which product a customer might want. The main families are supervised, unsupervised and reinforcement learning. ML is the foundation of modern AI, including the deep learning behind today's large language models.
Main types of machine learning
- Supervised learning: the model learns from labelled examples (inputs with the right answer) to predict or classify new cases.
- Unsupervised learning: the model finds structure in unlabelled data, such as customer segments or anomalies.
- Reinforcement learning: an agent learns by trial and error, receiving rewards or penalties for its actions.
- Self-supervised learning: the model creates its own training signal from the data, for example predicting the next word; this is how language models are pre-trained.
ML, deep learning and generative AI
Artificial intelligence is the broad field. Machine learning is the approach that learns from data. Deep learning is a type of ML that uses neural networks with many layers, and it drives image recognition, speech and language models. Generative AI is a use of deep learning that produces new content: text, images, code or audio.
In business, classic ML (forecasting, scoring, classification on tabular data) and generative AI usually coexist, each where it fits best.
What it takes in production
- Data that is relevant, sufficient and representative of the cases the model will see.
- A clear metric linked to the business decision, not only to model accuracy.
- Monitoring, because performance degrades when the real world drifts from the training data.
- Retraining, versioning and governance, usually organised as MLOps.
Frequently asked questions
What is the difference between AI and machine learning?
AI is the broad goal of making machines perform tasks that need intelligence. Machine learning is one way of achieving it, by learning from data. Almost all current AI systems, including large language models, are built with machine learning.
What is an example of machine learning?
A spam filter that learns from emails marked as spam is a classic example. Others include credit scoring, demand forecasting, product recommendations and predictive maintenance.
What is the difference between machine learning and deep learning?
Deep learning is a subset of machine learning that uses neural networks with many layers. It works especially well with images, audio and text, but usually needs more data and computing power than other ML methods.
Is a large language model machine learning?
Yes. A large language model is a deep learning model trained, mostly with self-supervised learning, on large amounts of text. It is one of the most visible results of machine learning today.
Do I need a lot of data for machine learning?
It depends on the problem and the method. Simple models on structured data can work with modest datasets, while deep learning from scratch needs much more. Starting from a pre-trained model and adapting it reduces the data you need.
How to put it to work
Where it shows up at Thinkia
Further reading
Related terms
Sources
- ISO/IEC · ISO/IEC 22989:2022, Artificial intelligence concepts and terminology (IEC webstore)
- Google for Developers · Machine Learning Crash Course announcement
- Samuel · Some Studies in Machine Learning Using the Game of Checkers (IBM Journal of Research and Development, 1959)
Updated: 2026-10-21