Content deleted Content added
lede rephrased; {{Machine learning|Paradigms}} |
image moved to the left and above the infobox |
||
Line 1:
{{Short description|Machine learning task}}
{{Machine learning|Paradigms}}▼
'''Unsupervised learning''', is paradigm in [[machine learning]] where, in contrast to [[supervised learning]] and [[semi-supervised learning]], algorithms learn patterns exclusively from unlabeled data.
Line 7 ⟶ 5:
=== Tasks vs. methods ===
[[File:Task-guidance.png|thumb|left|300px|Tendency for a task to employ supervised vs. unsupervised methods. Task names straddling circle boundaries is intentional. It shows that the classical division of imaginative tasks (left) employing unsupervised methods is blurred in today's learning schemes.]]▼
▲{{Machine learning|Paradigms}}
▲[[File:Task-guidance.png|thumb|300px|Tendency for a task to employ supervised vs. unsupervised methods. Task names straddling circle boundaries is intentional. It shows that the classical division of imaginative tasks (left) employing unsupervised methods is blurred in today's learning schemes.]]
Neural network tasks are often categorized as discriminative (recognition) or generative (imagination). Often but not always, discriminative tasks use supervised methods and generative tasks use unsupervised (see [[Venn diagram]]); however, the separation is very hazy. For example, object recognition favors supervised learning but unsupervised learning can also cluster objects into groups. Furthermore, as progress marches onward some tasks employ both methods, and some tasks swing from one to another. For example, image recognition started off as heavily supervised, but became hybrid by employing unsupervised pre-training, and then moved towards supervision again with the advent of [[Dilution_(neural_networks)|dropout]], [[Rectifier_(neural_networks)|ReLU]], and [[Learning_rate|adaptive learning rates]].
| |||