Sciweavers

2295 search results - page 328 / 459
» Learning Overcomplete Representations
Sort
View
AAAI
2011
12 years 10 months ago
Incorporating Boosted Regression Trees into Ecological Latent Variable Models
Important ecological phenomena are often observed indirectly. Consequently, probabilistic latent variable models provide an important tool, because they can include explicit model...
Rebecca A. Hutchinson, Li-Ping Liu, Thomas G. Diet...
ICALT
2005
IEEE
14 years 3 months ago
ActiveTutor
In this paper we present an architecture dedicated to an intelligently assisted educational tool which integrates within a unified framework software rational agents both at the m...
Jean Pierre Fournier
ICRA
2002
IEEE
141views Robotics» more  ICRA 2002»
14 years 3 months ago
Movement Imitation with Nonlinear Dynamical Systems in Humanoid Robots
This article presents a new approach to movement planning, on-line trajectory modiļ¬cation, and imitation learning by representing movement plans based on a set of nonlinear diļ¬...
Auke Jan Ijspeert, Jun Nakanishi, Stefan Schaal
MLMTA
2003
13 years 11 months ago
Using a Two-Layered Case-Based Reasoning for Prediction in Soccer Coach
Abstractā€” The prediction of the future states in MultiAgent Systems has been a challenging problem since the begining of MAS. Robotic soccer is a MAS environment in which the pre...
Mazda Ahmadi, Abolfazl Keighobadi Lamjiri, Mayssam...
NIPS
1993
13 years 11 months ago
Using Local Trajectory Optimizers to Speed Up Global Optimization in Dynamic Programming
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
Christopher G. Atkeson