Computing Gaussian Mixture Models with EM Using Equivalence Constraints
By Noam Shental, Aharon Bar-Hillel, Tomer Hertz, Daphna Weinshall. Neural Information Processing Systems, 2003
326 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/448f8d87f1709ffbdec46a7d5881f8c1f924d0e0
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Dacheng Tao
- Zhi-Hua Zhou
- Kilian Q. Weinberger
- Daniel Cohen-Or
- Jacob Goldberger
- Ruslan Salakhutdinov
- Yoshua Bengio
- Daoqiang Zhang
Citations in the corpus
- Semi-Supervised Dimensionality Reduction (2007, methodology): “Table 2: F-scores on Newsgroups data with 30% constraints Methods Different-300 Similar-300 same-300 Shental[14] 0.”
- Active co-analysis of a set of shapes (2012, methodology): “These constraints have been incorporated into many clustering algorithms, such as K-means clustering [Wagstaff and Cardie 2000], hierarchical clustering [Klein et al. 2002], and clustering with Gaussian mixture models [Shental et al. 2004].”
- Finite mixture models and model-based clustering (2010, methodology): “The development of “pairwise relations” [13, 75, 110] concerns the situation when some observations are known to belong to the same group (positive relation) or different groups (negative relation).”
- Hierarchical Clustering of a Mixture Model (2004, methodology): “[5] utilized the generative model described in the previous section and the EM algorithm derived from it, to learn a MoG from data set endowed with equivalence constraints that enforce equivalent points to be assigned to the same cluster.”
- Learning Distance Functions using Equivalence Relations (2003, methodology): “We have also recently developed a way to introduce both positive and negative equivalence relations into the EM algorithm for the estimation of a mixture of Gaussian models (Hertz et al., 2002; Shental et al., 2003).”
- Classes of Kernels for Machine Learning: A Statistics Perspective (2002, methodology): “Pairwise relations may arise from knowledge of domain experts [3], perceived similarity (or dissimilarity) [4], or even common sense [5].”