Sciweavers

1419 search results - page 228 / 284
» Approximation Methods for Supervised Learning
Sort
View
COLING
2008
15 years 1 months ago
Authorship Attribution and Verification with Many Authors and Limited Data
Most studies in statistical or machine learning based authorship attribution focus on two or a few authors. This leads to an overestimation of the importance of the features extra...
Kim Luyckx, Walter Daelemans
TFS
2008
129views more  TFS 2008»
14 years 10 months ago
A Functional-Link-Based Neurofuzzy Network for Nonlinear System Control
Abstract--This study presents a functional-link-based neurofuzzy network (FLNFN) structure for nonlinear system control. The proposed FLNFN model uses a functional link neural netw...
Cheng-Hung Chen, Cheng-Jian Lin, Chin-Teng Lin
ICRA
2010
IEEE
104views Robotics» more  ICRA 2010»
14 years 10 months ago
Using model knowledge for learning inverse dynamics
— In recent years, learning models from data has become an increasingly interesting tool for robotics, as it allows straightforward and accurate model approximation. However, in ...
Duy Nguyen-Tuong, Jan Peters
MICCAI
2009
Springer
15 years 6 months ago
On the Manifold Structure of the Space of Brain Images
This paper investigates an approach to model the space of brain images through a low-dimensional manifold. A data driven method to learn a manifold from a collections of brain imag...
Samuel Gerber, Tolga Tasdizen, Sarang C. Joshi, Ro...
ECML
2005
Springer
15 years 5 months ago
Natural Actor-Critic
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...
Jan Peters, Sethu Vijayakumar, Stefan Schaal