When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensional...
Abstract. Intensity based registration methods, such as the mutual information (MI), do not commonly consider the spatial geometric information and the initial correspondences are ...
Many applications in structure matching require the ability to search for graphs that are similar to a query graph, i.e., similarity graph queries. Prior works, especially in chem...
We propose a new method to partition an unlabeled dataset, called Discriminative Context Partitioning (DCP). It is motivated by the idea of splitting the dataset based only on how...
: Traffic distribution forecasting is an essential step in network planning for packet-switching networks. It is frequently necessary to forecast and develop an optimal network con...