Scaling up document-image classifiers to handle an unlimited variety of document and image types poses serious challenges to conventional trainable classifier technologies. Highly...
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...
A number of real-world domains such as social networks and e-commerce involve heterogeneous data that describes relations between multiple classes of entities. Understanding the n...
The probabilistic network technology is a knowledgebased technique which focuses on reasoning under uncertainty. Because of its well defined semantics and solid theoretical founda...
Background: Today it is common to apply multiple potentially conflicting data sources to a given phylogenetic problem. At the same time, several different inference techniques are...