Sciweavers

1656 search results - page 220 / 332
» Learning and Consistency
Sort
View
ECML
2007
Springer
14 years 3 months ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
GECCO
2007
Springer
158views Optimization» more  GECCO 2007»
14 years 3 months ago
A novel generative encoding for exploiting neural network sensor and output geometry
A significant problem for evolving artificial neural networks is that the physical arrangement of sensors and effectors is invisible to the evolutionary algorithm. For example,...
David B. D'Ambrosio, Kenneth O. Stanley
HUMO
2007
Springer
14 years 3 months ago
Multi-activity Tracking in LLE Body Pose Space
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
SAFECOMP
2007
Springer
14 years 3 months ago
Controller Architecture for Safe Cognitive Technical Systems
Abstract. Cognition of technical systems, as the ability to perceive situations, to learn about favorable behavior, and to autonomously generate decisions, adds new attributes to s...
Sebastian Kain, Hao Ding, Frank Schiller, Olaf Stu...
SAC
2006
ACM
14 years 3 months ago
Exploiting partial decision trees for feature subset selection in e-mail categorization
In this paper we propose PARTfs which adopts a supervised machine learning algorithm, namely partial decision trees, as a method for feature subset selection. In particular, it is...
Helmut Berger, Dieter Merkl, Michael Dittenbach