Sciweavers

7928 search results - page 108 / 1586
» Human-Like Learning Methods for a
Sort
View
153
Voted
ML
2012
ACM
385views Machine Learning» more  ML 2012»
13 years 11 months ago
An alternative view of variational Bayes and asymptotic approximations of free energy
Bayesian learning, widely used in many applied data-modeling problems, is often accomplished with approximation schemes because it requires intractable computation of the posterio...
Kazuho Watanabe
CVPR
2012
IEEE
13 years 6 months ago
Geometry constrained sparse coding for single image super-resolution
The choice of the over-complete dictionary that sparsely represents data is of prime importance for sparse codingbased image super-resolution. Sparse coding is a typical unsupervi...
Xiaoqiang Lu, Haoliang Yuan, Pingkun Yan, Yuan Yua...
108
Voted
DIDACTICA
2000
70views more  DIDACTICA 2000»
15 years 3 months ago
Visualisierung und Animation der semantischen Analyse von Programmen
In computer science methods to aid learning are very important, because abstract models are used frequently. For this conventional teaching methods do not suffice. We have develope...
Andreas Kerren
ECTEL
2007
Springer
15 years 9 months ago
Categorizing Learning Objects Based On Wikipedia as Substitute Corpus
As metadata is often not sufficiently provided by authors of Learning Resources, automatic metadata generation methods are used to create metadata afterwards. One kind of metadata ...
Marek Meyer, Christoph Rensing, Ralf Steinmetz
145
Voted
IROS
2006
IEEE
113views Robotics» more  IROS 2006»
15 years 9 months ago
Policy Gradient Methods for Robotics
— The aquisition and improvement of motor skills and control policies for robotics from trial and error is of essential importance if robots should ever leave precisely pre-struc...
Jan Peters, Stefan Schaal