619 search results - page 11 / 124 » On computational limitations of neural network architectures |
GECCO
2004
Springer
14 years 26 days ago
2004
Springer
Spiking neural networks are computationally more powerful than conventional artificial neural networks. Although this fact should make them especially desirable for use in evoluti...
IPPS
1998
IEEE
13 years 11 months ago
1998
IEEE
We derive cost formulae for three di erent parallelisation techniques for training supervised networks. These formulae are parameterised by properties of the target computer archit...
AIIA
2003
Springer
13 years 11 months ago
2003
Springer
A novel, two stage, neural architecture for the segmentation of range data and their modeling with undeformed superquadrics is presented. The system is composed by two distinct neu...
IPSN
2004
Springer
14 years 26 days ago
2004
Springer
We study network capacity limits and optimal routing algorithms for regular sensor networks, namely, square and torus grid sensor networks, in both, the static case (no node failu...
ICDAR
2003
IEEE
14 years 23 days ago
2003
IEEE
An automatic recognition of online handwritten text has been an on-going research problem for nearly four decades. It has been gaining more interest due to the increasing populari...