Machine learning: Difference between revisions

Revision as of 01:28, 25 June 2025

Revision as of 01:31, 25 June 2025

Line 84:

[[File:Supervised_and_unsupervised_learning.png|thumb|upright=1.3|In [[supervised learning]], the training data is labelled with the expected answers, while in [[unsupervised learning]], the model identifies patterns or structures in unlabelled data.]]

Machine learning approaches are traditionally divided into three broad categories, which correspond to learning paradigms, depending on the nature of the "signal" or "feedback" available to the learning system:

* [[Supervised learning]]: ItThe computer is typepresented ofwith machineexample learninginputs whereand thetheir algorithmdesired isoutputs, trainedgiven onby a labeled dataset"teacher", meaningand that eachthe inputgoal is pairedto withlearn a correspondinggeneral output.rule The objective is to learn athat [[Map (mathematics)|mapingmaps]] functioninputs thatto can predict the output for new, unseen inputsoutputs.

* [[Unsupervised learning]]: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end ([[feature learning]]).

* [[Reinforcement learning]]: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as [[Autonomous car|driving a vehicle]] or playing a game against an opponent). As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximise.<ref name="bishop2006"/>