Sciweavers

986 search results - page 76 / 198
» Zero-data Learning of New Tasks
Sort
View
AAAI
2010
14 years 6 months ago
Multilinear Maximum Distance Embedding Via L1-Norm Optimization
Dimensionality reduction plays an important role in many machine learning and pattern recognition tasks. In this paper, we present a novel dimensionality reduction algorithm calle...
Yang Liu, Yan Liu, Keith C. C. Chan
ICML
2009
IEEE
15 years 10 months ago
Trajectory prediction: learning to map situations to robot trajectories
Trajectory planning and optimization is a fundamental problem in articulated robotics. Algorithms used typically for this problem compute optimal trajectories from scratch in a ne...
Nikolay Jetchev, Marc Toussaint
SAB
2010
Springer
212views Optimization» more  SAB 2010»
14 years 7 months ago
A Study of Adaptive Locomotive Behaviors of a Biped Robot: Patterns Generation and Classification
Abstract. Neurobiological studies showed the important role of Centeral Pattern Generators for spinal cord in the control and sensory feedback of animals' locomotion. In this ...
John Nassour, Patrick Henaff, Fathi Ben Ouezdou, G...
ICIP
2007
IEEE
15 years 11 months ago
Extrapolating Learned Manifolds for Human Activity Recognition
The problem of human activity recognition via visual stimuli can be approached using manifold learning, since the silhouette (binary) images of a person undergoing a smooth motion...
Tat-Jun Chin, Liang Wang, Konrad Schindler, David ...
ICML
2005
IEEE
15 years 10 months ago
Interactive learning of mappings from visual percepts to actions
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...
Justus H. Piater, Sébastien Jodogne