: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
A system for the automatic segmentation of fluorescence micrographs is presented. In a first step positions of fluorescent cells are detected by a fast learning neural network, whi...
Tim W. Nattkemper, Heiko Wersing, Walter Schubert,...
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
Selecting a small set of nodes called pivots, from all the nodes in a network and maintaining the routing infrastructure to and among each other can reduce routing overhead and ex...
Multiobjective optimization deals with problems involving multiple measures of performance that should be optimized simultaneously. In this paper we extend bucket elimination (BE),...