Sciweavers

1800 search results - page 249 / 360
» Learning Restart Strategies
Sort
View
NIPS
2004
15 years 6 months ago
Object Classification from a Single Example Utilizing Class Relevance Metrics
We describe a framework for learning an object classifier from a single example. This goal is achieved by emphasizing the relevant dimensions for classification using available ex...
Michael Fink 0002
ICRA
2007
IEEE
160views Robotics» more  ICRA 2007»
15 years 11 months ago
Adaptive Sampling for Multi-Robot Wide-Area Exploration
— The exploration problem is a central issue in mobile robotics. A complete coverage is not practical if the environment is large with a few small hotspots, and the sampling cost...
Kian Hsiang Low, Geoffrey J. Gordon, John M. Dolan...
WIDM
2004
ACM
15 years 10 months ago
A comprehensive solution to the XML-to-relational mapping problem
The use of relational database management systems (RDBMSs) to store and query XML data has attracted considerable interest with a view to leveraging their powerful and reliable da...
Sihem Amer-Yahia, Fang Du, Juliana Freire
GECCO
2007
Springer
183views Optimization» more  GECCO 2007»
15 years 9 months ago
Evolving distributed agents for managing air traffic
Air traffic management offers an intriguing real world challenge to designing large scale distributed systems using evolutionary computation. The ability to evolve effective air t...
Adrian K. Agogino, Kagan Tumer
CVPR
2009
IEEE
17 years 11 days ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...