Sciweavers

1760 search results - page 274 / 352
» Learning from Partial Observations
Sort
View
ICML
2006
IEEE
16 years 7 months ago
Predictive linear-Gaussian models of controlled stochastic dynamical systems
We introduce the controlled predictive linearGaussian model (cPLG), a model that uses predictive state to model discrete-time dynamical systems with real-valued observations and v...
Matthew R. Rudary, Satinder P. Singh
TEI
2010
ACM
197views Hardware» more  TEI 2010»
16 years 1 months ago
Constructing with movement: kinematics
This paper describes Kinematics: a novel construction toy for children consisting of both active (shape-changing or rotating) and passive building blocks. In comparison to similar...
Leonhard Oschuetz, Daniel Wessolek, Wolfgang Sattl...
ICMI
2009
Springer
147views Biometrics» more  ICMI 2009»
16 years 23 days ago
Multimodal end-of-turn prediction in multi-party meetings
One of many skills required to engage properly in a conversation is to know the appropiate use of the rules of engagement. In order to engage properly in a conversation, a virtual...
Iwan de Kok, Dirk Heylen
IJCNN
2008
IEEE
16 years 18 days ago
Biologically realizable reward-modulated hebbian training for spiking neural networks
— Spiking neural networks have been shown capable of simulating sigmoidal artificial neural networks providing promising evidence that they too are universal function approximat...
Silvia Ferrari, Bhavesh Mehta, Gianluca Di Muro, A...
EPIA
2007
Springer
16 years 11 days ago
Human Robot Interaction Based on Bayesian Analysis of Human Movements
We present as a contribution to the field of human-machine interaction a system that analyzes human movements online, based on the concept of Laban Movement Analysis (LMA). The im...
Jörg Rett, Jorge Dias