Abstract. We propose a non-standard neural network called TPNN which offers the direct mapping from a peptide sequence to a property of interest in order to model the quantitative ...
This paper presents a novel method for reconstructing complex 3D objects with unknown topology using silhouettes extracted from image sequences. This method exploits the duality p...
Title of thesis: BOOTSTRAPPING FREE-SPACE OPTICAL NETWORKS Fang Liu, Master of Science, 2004 Thesis directed by: Professor Uzi Vishkin Department of Electrical and Computer Engine...
This paper presents a variational method for supervised texture segmentation, which is based on ideas coming from the curve propagation theory. We assume that a preferable texture...
The self-organising map (SOM) has been successfully employed as a nonparametric method for dimensionality reduction and data visualisation. However, for visualisation the SOM requ...