Unsupervised learning is a type of @Machine Learning (ML) in which algorithms analyze data without labeled responses or explicit instruction. Rather than being guided by a known outcome, the @algorithm seeks to discover patterns, groupings, or structures inherent within the data itself. Common techniques include clustering—such as k-means or hierarchical clustering—and dimensionality reduction methods like principal component analysis (PCA). Unsupervised learning is widely applied for exploratory data analysis, anomaly detection, and as a preprocessing step in more complex workflows. Its focus on pattern discovery makes it distinct from supervised learning, where models learn from explicitly labeled examples.

Contexts

• #ai-lexicon
• #artificial-intelligence