unsupervised learning
Sign in to saveAlso known as unsupervised machine learning
machine learning technique
Research
14,328 papers- Demystifying unsupervised learning: how it helps and hurts.Trends in cognitive sciences · 2024
- Segment-Based Unsupervised Learning Method in Sensor-Based Human Activity Recognition.Sensors (Basel, Switzerland) · 2023
- Unsupervised graph-level representation learning with hierarchical contrasts.Neural networks : the official journal of the International Neural Network Society · 2023
- A new concept of unsupervised learning: directed self-guided learning in the health professions.Academic medicine : journal of the Association of American Medical Colleges · 2010
- Unsupervised learning for robust working memory.PLoS computational biology · 2022
via PubMed
Wikidata facts
Show 2 more facts
- ACM Classification Code (2012)
- 10010260
- Commons category
- Unsupervised learning
Sources (3)
via Wikidata · CC0
~15 min read
Article
Unsupervised learning is a framework in machine learning where, in contrast to supervised learning, algorithms learn patterns exclusively from unlabeled data. Other frameworks in the spectrum of supervisions include weak- or semi-supervision, where a small portion of the data is tagged, and self-supervision. Some researchers consider self-supervised learning a form of unsupervised learning.
Conceptually, unsupervised learning divides into the aspects of data, training, algorithm, and downstream applications. Typically, the dataset is harvested cheaply "in the wild", such as massive text corpus obtained by web crawling, with only minor filtering (such as Common Crawl). This compares favorably to supervised learning, where the dataset (such as the ImageNet1000) is typically constructed manually, which is much more expensive.