Learn AI / Learning Paths /How AI learns
How AI learns
From a pile of examples to a working model, one mechanism at a time. The engine-room tour.
Data
Recorded observations, measurements or examples that people or systems can store, examine and use for a purpose.
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.
Label
The expected answer attached to an example so a model can learn what output should match that input.
Supervised learning
A method for training a model on examples paired with target outputs, so it can predict outputs for new inputs.
Neural network
A neural network is a layered set of connected numerical operations that turns input data into an output such as a label, score or prediction.
Error and loss
Error describes a mismatch between an output and a reference. Loss is a scalar training objective for one case or an aggregate across cases.
Gradient descent
A method for reducing a model’s loss by repeatedly adjusting its internal settings in the direction opposite the loss gradient.
Backpropagation
A method that propagates derivatives backwards through a model to compute how changes to each weight would affect the loss.
Overfitting
A model fits its training examples so closely that its performance drops on new cases.
Generalisation
The ability of a model to give useful results on new cases, not just on the examples used to build or tune it.