Sciweavers

777 search results - page 71 / 156
» Learning dynamic algorithm portfolios
Sort
View
FLAIRS
2001
15 years 4 months ago
Time Series Analysis Using Unsupervised Construction of Hierarchical Classifiers
Recently we have proposed an algorithm of constructing hierarchical neural network classifiers (HNNC), that is based on a modification of error back-propagation. This algorithm co...
S. A. Dolenko, Yu. V. Orlov, I. G. Persiantsev, Ju...
ATAL
2008
Springer
15 years 5 months ago
Sequential decision making in repeated coalition formation under uncertainty
The problem of coalition formation when agents are uncertain about the types or capabilities of their potential partners is a critical one. In [3] a Bayesian reinforcement learnin...
Georgios Chalkiadakis, Craig Boutilier
MM
2003
ACM
241views Multimedia» more  MM 2003»
15 years 8 months ago
Invariance in motion analysis of videos
In this paper, we propose an approach that retrieves motion of objects from the videos based on the dynamic time warping of view invariant characteristics. The motion is represent...
Cen Rao, Mubarak Shah, Tanveer Fathima Syeda-Mahmo...
ICRA
2003
IEEE
114views Robotics» more  ICRA 2003»
15 years 8 months ago
Robotic catching using a direct mapping from visual information to motor command
— In this paper a robotic catching algorithm based on a nonlinear mapping of visual information to the desired trajectory is proposed. The nonlinear mapping is optimized by learn...
Akio Namiki, Masatoshi Ishikawa
NIPS
2001
15 years 4 months ago
Scaling Laws and Local Minima in Hebbian ICA
We study the dynamics of a Hebbian ICA algorithm extracting a single non-Gaussian component from a high-dimensional Gaussian background. For both on-line and batch learning we fin...
Magnus Rattray, Gleb Basalyga