Learn AI / Term Explorer /How Machines Learn
How Machines Learn
Learning from examples instead of following written rules: what goes in, what changes inside, and what comes out.
Starter
Classification
A machine learning method that assigns one or more predefined category labels to an input based on learned patterns.
Feature
A feature is a piece of input information a model uses to help produce an output, such as a prediction, score or grouping.
Inference
Using a trained model on new input to produce an output such as a score, category, translation or generated text.
Label
The expected answer attached to an example so a model can learn what output should match that input.
Prediction
The result a model produces from input, such as a class, number, ranking or next token.
Supervised learning
A method for training a model on examples paired with target outputs, so it can predict outputs for new inputs.
Training
Training is the process of adjusting a model's parameters using data or feedback to improve performance on a learning objective.
Training example
A single row of training data used to adjust a model, often made of input values and, in some methods, a target answer.
Intermediate
Clustering
A method that groups similar examples together so patterns in data can be found without pre-written categories.
Ground truth
The checked reference answer used to train or evaluate a model, so its output can be compared with the best available real-world answer.
Regression
A supervised learning method that learns from example inputs and known target values to predict a numeric quantity for a new input.
Reinforcement learning
A training method that aims to improve behaviour through trial, feedback and cumulative reward across a sequence of actions.
Self-supervised learning
A training approach that creates its own learning targets from raw data, so a model can learn useful patterns without manual labels.
Semi-supervised learning
A learning approach that combines labelled and unlabelled examples to train a predictor for the same target task.
Transfer learning
Reusing patterns learned on one task or dataset to help a model learn a related task faster and with less new data.
Unsupervised learning
A way of training a model on unlabelled data to identify possible structure, similarities, groups or unusual cases without target answers for each example.
Validation and test sets
Separate portions of data are kept aside to tune a model during development and then to check, at the end, how well it works on unseen examples.