Proceedings of the 1998 conference on Advances in neural information processing systems II
Flexible discriminant and mixture models
Statistics and neural networks
Unsupervised learning by probabilistic latent semantic analysis
Machine Learning
Clustering based on conditional distributions in an auxiliary space
Neural Computation
Bankruptcy analysis with self-organizing maps in learning metrics
IEEE Transactions on Neural Networks
Sequential information bottleneck for finite data
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Supervised evaluation of Voronoi partitions
Intelligent Data Analysis
Supervised Gravitational Clustering with Bipolar Fuzzification
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Artificial Intelligence
Using supervised clustering to enhance classifiers
ISMIS'05 Proceedings of the 15th international conference on Foundations of Intelligent Systems
Discriminative clustering for market segmentation
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
How to "alternatize" a clustering algorithm
Data Mining and Knowledge Discovery
Large margin principle in hyperrectangle learning
Neurocomputing
Enhancing K-Means using class labels
Intelligent Data Analysis
Hi-index | 0.00 |
The learning metrics principle describes a way to derive metrics to the data space from paired data. Variation of the primary data is assumed relevant only to the extent it causes changes in the auxiliary data. Discriminative clustering finds clusters of primary data that are homogeneous in the auxiliary data. In this paper, discriminative clustering using a mutual information criterion is shown to be asymptotically equivalent to vector quantization in learning metrics. We also present a new, finite-data variant of discriminative clustering and show that it builds contingency tables that detect optimally statistical dependency between the clusters and the auxiliary data. A finite-data algorithm is demonstrated to outperform the older mutual information maximizing variant.