28 search results - page 4 / 6 » Using the BSP Cost Model to Optimise Parallel Neural Network... |
167
Voted
ICDAR
2011
IEEE
14 years 3 months ago
2011
IEEE
—To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on...
101
Voted
ESANN
2000
15 years 4 months ago
2000
In modelling the development of the oculomotor control system using neural networks, it is important to determine the appropriate cost function on which to train the models. Whilst...
103
click to vote
ICANN
2005
Springer
15 years 9 months ago
2005
Springer
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require ite...
128
Voted
NECO
2007
15 years 3 months ago
2007
It is well-known that, in unidentifiable models, the Bayes estimation provides much better generalization performance than the maximum likelihood (ML) estimation. However, its ac...
169
click to vote
IJCNN
2007
IEEE
15 years 9 months ago
2007
IEEE
Abstract— The optimal model parameters of a kernel machine are typically given by the solution of a convex optimisation problem with a single global optimum. Obtaining the best p...