237 search results - page 2 / 48 » A Quantitative Theory of Neural Computation |
ICIAR
2007
Springer
14 years 1 months ago
2007
Springer
Abstract. We describe the implementation of a 2D optical flow algorithm published in the European Conference on Computer Vision (ECCV 2004) by Brox et al. [1] (best paper award) a...
RSCTC
2000
Springer
13 years 11 months ago
2000
Springer
This paper introduces a neural network architecture based on rough sets and rough membership functions. The neurons of such networks instantiate approximate reasoning in assessing ...
NN
1998
Springer
13 years 7 months ago
1998
Springer
There are many applications of multilayer neural networks to pattern classification problems in the engineering field. Recently, it has been shown that Bayes a posteriori probab...
CIE
2005
Springer
14 years 28 days ago
2005
Springer
We promote the concept of object directed computability in computational geometry in order to faithfully generalise the wellestablished theory of computability for real numbers and...
ESANN
2007
13 years 8 months ago
2007
Training recurrent neural networks is hard. Recently it has however been discovered that it is possible to just construct a random recurrent topology, and only train a single linea...