Sciweavers

2175 search results - page 254 / 435
» Model-free Learning from Demonstration
Sort
View
JMLR
2010
119views more  JMLR 2010»
13 years 3 months ago
Factorized Orthogonal Latent Spaces
Existing approaches to multi-view learning are particularly effective when the views are either independent (i.e, multi-kernel approaches) or fully dependent (i.e., shared latent ...
Mathieu Salzmann, Carl Henrik Ek, Raquel Urtasun, ...
TSMC
2010
13 years 3 months ago
Interactive Teaching for Vision-Based Mobile Robots: A Sensory-Motor Approach
Abstract--For the last decade, we have developed a visionbased architecture for mobile robot navigation. Our bio-inspired model of the navigation has proved to achieve sensory-moto...
Christophe Giovannangeli, Philippe Gaussier
KDD
2009
ACM
142views Data Mining» more  KDD 2009»
14 years 9 months ago
Quantification and semi-supervised classification methods for handling changes in class distribution
In realistic settings the prevalence of a class may change after a classifier is induced and this will degrade the performance of the classifier. Further complicating this scenari...
Jack Chongjie Xue, Gary M. Weiss
VLDB
2007
ACM
129views Database» more  VLDB 2007»
14 years 3 months ago
Processing Forecasting Queries
Forecasting future events based on historic data is useful in many domains like system management, adaptive query processing, environmental monitoring, and financial planning. We...
Songyun Duan, Shivnath Babu
ECAI
2006
Springer
14 years 22 days ago
Automatic Generation of Implied Constraints
Abstract. A well-known difficulty with solving Constraint Satisfaction Problems (CSPs) is that, while one formulation of a CSP may enable a solver to solve it quickly, a different ...
John Charnley, Simon Colton, Ian Miguel