Machine Learning (ML)
A subset of AI where systems learn patterns from data rather than following explicitly programmed rules.
Definition
Machine learning is a method of building AI systems where algorithms discover patterns in training data and build statistical models, enabling predictions or decisions on unseen data. The core insight: instead of programming rules manually, we show the system examples and let it infer the rules.
The three main ML paradigms are supervised learning (labelled input-output pairs), unsupervised learning (finding structure in unlabelled data), and reinforcement learning (learning from reward signals). Common algorithms include linear regression, decision trees, random forests, support vector machines, and neural networks.
Modern ML is dominated by deep learning — large neural networks trained on massive datasets — which has dramatically outperformed classical ML on perception tasks like image recognition and natural language processing.
Examples
- Netflix recommendations
- Gmail spam filter
- Credit card fraud detection
- Google Translate
Want a deeper dive?
Read our full explainer with use cases, how-it-works, and FAQs.
Machine Learning concept guideCompanies using this
Related Terms
Deep Learning
A subset of machine learning using neural networks with many layers to learn complex hierarchical representations.
Supervised Learning
Training ML models on labelled input-output pairs to learn a function mapping inputs to target outputs.
Unsupervised Learning
Finding patterns, structure, or representations in data without labelled examples.
Reinforcement Learning (RL)
A learning paradigm where an agent learns by taking actions in an environment and receiving reward signals.
Neural Network
A computing system of interconnected nodes inspired by biological brains, trained to recognise patterns.