Sciweavers

2210 search results - page 228 / 442
» Information complexity of neural networks
Sort
View
ESANN
2006
15 years 8 months ago
Recognition of handwritten digits using sparse codes generated by local feature extraction methods
We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritte...
Rebecca Steinert, Martin Rehn, Anders Lansner
ESANN
2000
15 years 8 months ago
Parametric approach to blind deconvolution of nonlinear channels
A parametric procedure for the blind inversion of nonlinear channels is proposed, based on a recent method of blind source separation in nonlinear mixtures. Experiments show that ...
Jordi Solé i Casals, Anisse Taleb, Christia...
ICASSP
2011
IEEE
14 years 10 months ago
Audio recognition in the wild: Static and dynamic classification on a real-world database of animal vocalizations
We present a study on purely data-based recognition of animal sounds, performing evaluation on a real-world database obtained from the Humboldt-University Animal Sound Archive. As...
Felix Weninger, Björn Schuller
ICDCSW
2003
IEEE
15 years 12 months ago
Tuples On The Air: A Middleware for Context-Aware Computing in Dynamic Networks
We present TOTA (“Tuples On The Air”), a novel middleware for supporting adaptive context-aware activities in dynamic network scenarios. The key idea in TOTA is to rely on spa...
Marco Mamei, Franco Zambonelli, Letizia Leonardi
DAMON
2009
Springer
16 years 1 months ago
Spinning relations: high-speed networks for distributed join processing
By leveraging modern networking hardware (RDMA-enabled network cards), we can shift priorities in distributed database processing significantly. Complex and sophisticated mechani...
Philip Werner Frey, Romulo Goncalves, Martin L. Ke...