A branch of AI in which computers learn patterns from data to make predictions or decisions without being explicitly programmed for each case.
In traditional programming, a developer writes rules: if an email contains certain words, mark it as spam. In machine learning, the developer provides many examples of spam and legitimate email, and an algorithm learns the patterns that distinguish them, often catching cases no human would have written a rule for.
Machine learning is commonly divided into supervised learning, which uses labeled examples; unsupervised learning, which finds structure in unlabeled data; and reinforcement learning, which learns through trial and reward. Applications include recommendation engines, fraud detection, demand forecasting, medical image analysis, and speech recognition. Success depends heavily on data quality, sensible evaluation, and avoiding problems such as overfitting and biased training data.
Educational technology that adjusts content, difficulty, and pacing for each learner based on how they perform.
Algorithmic BiasSystematic errors in an algorithm or AI model that produce unfair outcomes for certain people or groups.
Deep LearningA branch of machine learning that uses neural networks with many layers to learn patterns from large amounts of data.
Model DriftThe gradual decline in an AI model's accuracy as real-world data or conditions change from those it was trained on.
Neural NetworkA machine learning model made of layers of connected nodes, loosely inspired by the brain, that learns patterns by adjusting connection weights.
Optical Character RecognitionTechnology, known as OCR, that reads printed or handwritten text in images and scanned documents and turns it into editable text.
OverfittingWhen a machine learning model learns its training data too closely, including noise, and performs poorly on new, unseen data.
Predictive AnalyticsUsing historical data, statistics, and machine learning to forecast future outcomes or behaviors.
PythonA popular, general-purpose programming language known for readable syntax, widely used in AI, data science, automation, and web development.
Reinforcement LearningA type of machine learning in which an agent learns by trial and error, receiving rewards or penalties for its actions.
Sentiment AnalysisUsing natural language processing to determine whether a piece of text expresses a positive, negative, or neutral opinion.
Supervised LearningA machine learning approach where a model learns from labeled examples, each pairing an input with the correct output.
Synthetic DataArtificially generated data that mimics the patterns of real data, used for testing, training models, or sharing without exposing real records.
Unsupervised LearningA machine learning approach that finds patterns and structure in data that has no labels or predefined answers.
A step-by-step software engineering roadmap with skills, milestones and realistic timelines, plus how to land your first developer role with or without a degree.
AI is reshaping tech roles, but strong fundamentals still win jobs. Here are the skills employers are prioritising in 2026 and a practical plan to build them.
How large language models work in plain English, from tokens and training to next-word prediction, with a simple diagram and no math.