k-means clustering, principal component analysis (PCA) and DBSCAN; others include hierarchical clustering, Gaussian mixture models, isolation forest and autoencoders. Clustering and anomaly detection are tasks rather than algorithms.
Card 1 of 259. Answer: k-means clustering, principal component analysis (PCA) and DBSCAN; others include hierarchical clustering, Gaussian mixture models, isolation forest and autoencoders. Clustering and anomaly detection are tasks rather than algorithms.
About · Quizzes · History of AI · To suggest new questions or report an error send me a dm.
Three standard answers are k-means clustering, principal component analysis (PCA) and DBSCAN; hierarchical clustering, Gaussian mixture models, isolation forest and autoencoders also count. All learn from features alone, with no target. Name concrete algorithms: clustering and anomaly detection are tasks, not algorithms.
Show that you know what each does. k-means assigns each point to the nearest of k centroids, moves each centroid to the mean of its points, and repeats until nothing changes. PCA projects data onto the orthogonal directions of greatest variance. A Gaussian mixture gives soft memberships: with two equally weighted components, means 0 and 4, standard deviation 1, a point at 2.5 belongs 88% to the second and 12% to the first.
Expect a follow-up on choosing between them. k-means needs k in advance and favors round clusters of similar size. DBSCAN finds clusters of any shape and labels outliers as noise, but struggles when density varies. Hierarchical clustering gives a dendrogram you can cut at any level, but needs all pairwise distances, so it scales poorly.
