Spectral Clustering
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.
Izvorni zapis
Citati kopirani doslovno iz izvornog zapisa metode. Ne impliciraju nikakvu provjeru na razini tvrdnje.
- 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. · URL
- von Luxburg, U. (2007). A Tutorial on Spectral Clustering. Statistics and Computing, 17, 395–416. · DOI 10.1007/s11222-007-9033-z
- Shi, J., & Malik, J. (2000). Normalized Cuts and Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888–905. · DOI 10.1109/34.868688
Uređene tvrdnje
Tvrdnje pohranjene u knjigu dokaza, svaka s vlastitom procjenom.
Ovaj prikaz ne izmišlja procjenu tvrdnje kada knjiga dokaza nema nijednu.
Povezane metode
Generirano iz grafa metode i prikazano kao strojno predložene relacije — ne implicira se nikakva tvrdnja dokaza.