Sciweavers

2924 search results - page 306 / 585
» On the Use of Evidence in Neural Networks
Sort
View
ICDAR
2009
IEEE
15 years 4 months ago
Invariant Primitives for Handwritten Arabic Script: A Contrastive Study of Four Feature Sets
The choice of relevant features is very decisive in handwriting recognition rate. Our aim is to present some useful structural and statistical features and see their degree of var...
Sofiene Haboubi, Samia Maddouri, Noureddine Ellouz...
NC
2011
175views Neural Networks» more  NC 2011»
15 years 1 months ago
P systems with active membranes: trading time for space
We consider recognizer P systems having three polarizations associated to the membranes, and we show that they are able to solve the PSPACEcomplete problem Quantified 3SAT when wo...
Antonio E. Porreca, Alberto Leporati, Giancarlo Ma...
ICASSP
2011
IEEE
14 years 10 months ago
Multichannel EEG analysis based on multi-scale multi-information
Functional connectivity has been widely used to reveal the dependencies between signals in complex networks such as neural networks observed from electroencephalogram (EEG) data. ...
Ying Liu, Selin Aviyente
ICANN
2005
Springer
16 years 6 days ago
Learning Features of Intermediate Complexity for the Recognition of Biological Motion
Humans can recognize biological motion from strongly impoverished stimuli, like point-light displays. Although the neural mechanism underlying this robust perceptual process have n...
Rodrigo Sigala, Thomas Serre, Tomaso Poggio, Marti...
CCECE
2006
IEEE
16 years 23 days ago
Adaptive Bilateral Control using Operator Elbow Impedance
— Human arm dynamics can be used for control of human-machine interfaces in haptic applications. In this paper, a novel method for online estimation of human operator elbow imped...
Farid Mobasser, Keyvan Hashtrudi-Zaad