We discuss an idea for collecting data in a relatively efficient manner. Our point of view is Bayesian and information-theoretic: on any given trial, we want to adaptively choose...
The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists of a network of input units driving...
An increasing number of comfortable publishing systems nowadays leads to documents containing more than just textual information. Graphics and images are combined with text and of...
The widespread use of RDF-based information necessitates efficient information retrieval techniques in wide-area networks. In this paper, we present Dynamic Semantic Space, a sche...
Today information management technology faces two major related challenges. One is to tame the information and options explosion that are upon us. Another is to support the inform...