Check our tutorials on state-of-the-art clustering methods!
| Acronym | Data Type | Software | Note | |
| CPF | Multivariate | Tutorial | GitHub | CPF (Component-wise Peak-Finding) is an improvement over DCF: (1) it applies the density peaks methodology within level sets of the estimated density; (2) the algorithm is not affected by spurious maxima of the density. |
| DCF | Multivariate | Slides Tutorial |
GitHub | DCF (Density Core Finding) is able to detect clusters of varying density and irregular shape, and
applicable to big data with numerous clusters. The idea is to detect high-density core regions, each region representing a cluster, and then assign each non-core point to the same cluster as its nearest neighbor of higher density. |
| FAEclust | Functional | Slides Poster |
GitHub | FAEclust is a novel functional autoencoder framework for the cluster analysis of multi-dimensional functional data. |
| GPmix | Functional | Slides Poster |
PyPI | GPmix (Gaussian Process mixture) is for the cluster analysis of
one-dimensional functional data. It is built on the property that the projection coefficients of the functional data onto any given projection function follow a univariate Gaussian mixture model. |
| Anonymous | Functional | Slides Tutorial |
GitHub | |
| REM | Multivariate | Slides Tutorial |
PyPI | REM (Reinforced EM) provides an efficient solution to the initilization problem of the EM algorithm for clustering with Gaussian mixture models. It initializes the Gaussian means with density-peak exemplars in the data. |