In traditional text clustering methods, documents are represented as "bags of words" without considering the semantic information of each document. For instance, if two ...
Xiaohua Hu, Xiaodan Zhang, Caimei Lu, E. K. Park, ...
Service composition concerns both integration of heterogeneous distributed applications and dynamic selection of services. QoS-aware selection enables a service requester with cer...
Davide Bacciu, Maria Grazia Buscemi, Lusine Mkrtch...
Background: The prediction of ancestral protein sequences from multiple sequence alignments is useful for many bioinformatics analyses. Predicting ancestral sequences is not a sim...
Large scale learning is often realistic only in a semi-supervised setting where a small set of labeled examples is available together with a large collection of unlabeled data. In...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...