手法を比較
選択した手法を並べて確認できます。異なる行はハイライト表示されます。
| K平均法クラスタリング× | スペクトラルクラスタリング× | |
|---|---|---|
| 分野 | 機械学習 | 機械学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 1967 | 2002 |
| 提唱者≠ | MacQueen, J. | Ng, A. Y.; Jordan, M. I.; Weiss, Y. |
| 種類≠ | Partitional clustering (centroid-based) | Graph-based clustering (spectral method) |
| 原典≠ | MacQueen, J. (1967). Some Methods for Classification and Analysis of Multivariate Observations. Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, 1, 281–297. link ↗ | Ng, A. Y., Jordan, M. I., & Weiss, Y. (2002). On Spectral Clustering: Analysis and an Algorithm. Advances in Neural Information Processing Systems, 14, 849–856. link ↗ |
| 別名≠ | K-Ortalamalar Kümeleme, k-ortalamalar kümeleme, k-means, centroid clustering | NJW spectral clustering, graph Laplacian clustering, normalized spectral clustering, spectral graph clustering |
| 関連≠ | 3 | 5 |
| 概要≠ | K-Means Clustering is a centroid-based partitional clustering algorithm, traced to J. MacQueen in 1967, that splits data into k clusters by assigning each observation to its nearest cluster centre. It is widely used for marketing segmentation, customer grouping, and exploratory analysis. | Spectral Clustering is a graph-based unsupervised learning algorithm, formalized by Ng, Jordan, and Weiss in 2002, that maps data points into a low-dimensional eigenspace derived from the similarity graph's Laplacian before applying k-means. This spectral embedding makes it possible to recover clusters of arbitrary shape — rings, crescents, interleaved spirals — that Euclidean distance-based methods consistently fail to separate. |
| ScholarGateデータセット ↗ |
|
|