This poster describes methods to enable intelligent access to multimodal information streams. We illustrate these methods in two integrated systems: the Broadcast News Editor (BNE...
We present a fast method that adaptively approximates large-scale functional scattered data sets with hierarchical B-splines. The scheme is memory efficient, easy to implement an...
Much contemporary development process research is based on analyses of process steps, their duration, and the events they propagate. Our initial research in large, mature telecomm...
Hierarchical matrices (H-matrices) approximate matrices in a data-sparse way, and the approximate arithmetic for H-matrices is almost optimal. In this paper we present an algebrai...
We investigate a form of modular neural network for classification with (a) pre-separated input vectors entering its specialist (expert) networks, (b) specialist networks which ar...