// ◇ Classical Machine Learning
DBSCAN (Density-Based Clustering)
Clusters by local density; finds arbitrarily shaped clusters and flags noise.
DBSCAN 密度聚类 1996 Foundational extended
IN PLAIN WORDS
A point with enough neighbours within radius ε is a core point; core points that reach each other form a cluster and isolated points are noise. No need to choose the number of clusters, and it handles non-spherical shapes that k-means cannot, but it is sensitive to ε and the minimum-neighbour count.
Used in: Geospatial clustering, anomaly detection, clustering embedding vectors
01Original paper
A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise
Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu · KDD-96 · 1996
Open ↗ ✓ Verified · 官方页面 HTTP 核实
02Where it sits
Learn the left column first; the right column builds on this one.
Learn first
Then you can learn
- Nothing in the atlas builds on it yet
Related:UMAPExpectation–Maximization (EM)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-22.
- JSON: /api/learn/algorithms.json (id:
dbscan)