Sciweavers

3256 search results - page 30 / 652
» Learning Linear Transformations
Sort
View
EAAI
2006
157views more  EAAI 2006»
13 years 7 months ago
Blind source separation based on self-organizing neural network
This contribution describes a neural network that self-organizes to recover the underlying original sources from typical sensor signals. No particular information is required abou...
Anke Meyer-Bäse, Peter Gruber, Fabian J. Thei...
ISBI
2004
IEEE
14 years 8 months ago
Enhanced Snake-Based Segmentation of Vocal Folds
We present a system to segment the medial edges of the vocal folds from stroboscopic video. The system has two components. The first learns a color transformation that optimally d...
Sonya Allin, John M. Galeotti, George D. Stetten, ...
ICASSP
2009
IEEE
14 years 2 months ago
Compressive sensing for sparsely excited speech signals
Compressive sensing (CS) has been proposed for signals with sparsity in a linear transform domain. We explore a signal dependent unknown linear transform, namely the impulse respo...
Thippur V. Sreenivas, W. Bastiaan Kleijn
IANDC
2008
109views more  IANDC 2008»
13 years 7 months ago
Compositions of extended top-down tree transducers
Abstract. Unfortunately the class of transformations computed by nondeleting and linear extended top-down tree transducers [Graehl, Knight: Training Tree Transducers. HLT-NAACL 200...
Andreas Maletti
CVPR
2007
IEEE
13 years 9 months ago
Kernel Fukunaga-Koontz Transform Subspaces For Enhanced Face Recognition
Traditional linear Fukunaga-Koontz Transform (FKT) [1] is a powerful discriminative subspaces building approach. Previous work has successfully extended FKT to be able to deal wit...
Yung-hui Li, Marios Savvides