E. P. Xing and R. M. Karp. Cli : Clustering of high-dimensional microarray data via iterative feature ltering using normalized cuts. In ISMB, 2001. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Learning Hierarchical Hidden Markov Models for Video.. - Xie, Chang, Divakaran, .. (2002) (Correct)
.... work address the supervised learning scenario, and evaluate the fitness of feature with regard to its information gain against training labels (filter ) or the quality of learned classifiers (wrapper ) For unsupervised learning on spatial data (i.e. assume samples are independent) Xing et al. XK01] iterated between cluster assignment and filter wrapper methods for known number of clusters; Dy and Brodley [DB00] used scatter separability and maximum likelihood (ML) criteria to evaluate fitness of features. To the best of our knowledge, no prior work has been reported for our problem of ....
....back to step 1 with i = i 1 if F is non empty. 5. For each feature model combination i , evaluate their fitness using the normalized BIC criteria in sec. 6.4, rank the feature subsets, and interpret the meanings of the resulting clusters. 6. 2 Evaluating information gain Information gain [XK01] measures the degree of agreement of each feature to the reference partition. We label a partition Q of the original set X F = X as integers Q # 1, N , let the probability of each part be the empirical portion (eq. 43) and define similarly the conditional probability of the ....
[Article contains additional citation context not shown here]
Eric P. Xing and Richard M. Karp. Cli#: Clustering of high-dimensional microarray data via iterative feature filtering using normalized cuts. In Proceedings of the Ninth International Conference on Intelligence Systems for Molecular Biology (ISMB), pages 1--9, 2001.
Feature Selection for High-Dimensional Genomic Microarray Data - Xing, Jordan, Karp (2001) (10 citations) Self-citation (Xing Karp) (Correct)
....than using the IG lter alone. While neither approach performs as well as Markov Blanket ltering, the MM lter has the advantage that it does not require class labels. This opens up the possibility of doing feature selection on this data set in the context of unsupervised clustering (see Xing Karp, 2001). In some high dimensional problems, it may be possible to bypass feature selection algorithms and obtain reasonable classi cation performance by choosing random subsets of features. That this is not the case in the Leukemia data set is shown by the results (Table 1) In the experiments reported ....
Xing, E. P., & Karp, R. M. (2001). Cli : Clustering of high-dimensional microarray data via iterative feature ltering using normalized cuts. Proceedings of the Nineteenth International Conference on Intelligent Systems for Molecular Biology.
Feature Selection for High-Dimensional Genomic Microarray Data - Xing, Jordan, Karp (2001) (10 citations) Self-citation (Xing Karp) (Correct)
....than using the IG filter alone. While neither approach performs as well as Markov Blanket filtering, the MM filter has the advantage that it does not require class labels. This opens up the possibility of doing feature selection on this data set in the context of unsupervised clustering (see Xing Karp, 2001). In some high dimensional problems, it may be possible to bypass feature selection algorithms and obtain reasonable classification performance by choosing random subsets of features. That this is not the case in the Leukemia data set is shown by the results (Table 1) In the experiments reported ....
Xing, E. P., & Karp, R. M. (2001). Cli#: Clustering of high-dimensional microarray data via iterative feature filtering using normalized cuts. Proceedings of the Nineteenth International Conference on Intelligent Systems for Molecular Biology.
Unknown - (Correct)
No context found.
E. P. Xing and R. M. Karp. Cli : Clustering of high-dimensional microarray data via iterative feature ltering using normalized cuts. In ISMB, 2001.
Unknown - (Correct)
No context found.
E. P. Xing and R. M. Karp. Cli : Clustering of high-dimensional microarray data via iterative feature ltering using normalized cuts. In ISMB, 2001.
On Semidefinite Relaxations for Normalized k-Cut and.. - Xing, Jordan (2003) (Correct)
No context found.
E. P. Xing and R. M. Karp. Cli : Clustering of high-dimensional microarray data via iterative feature ltering using normalized cuts. In ISMB, 2001.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC