Sciweavers

986 search results - page 84 / 198
» Zero-data Learning of New Tasks
Sort
View
CVPR
2005
IEEE
15 years 12 months ago
Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...
Evgeniy Bart, Shimon Ullman
CVPR
2004
IEEE
15 years 12 months ago
Automatic Cascade Training with Perturbation Bias
Face detection methods based on a cascade architecture have demonstrated fast and robust performance. Cascade learning is aided by the modularity of the architecture in which node...
Jie Sun, James M. Rehg, Aaron F. Bobick
BMCBI
2010
119views more  BMCBI 2010»
14 years 10 months ago
Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico study
Background: Gene silencing using exogenous small interfering RNAs (siRNAs) is now a widespread molecular tool for gene functional study and new-drug target identification. The key...
Qi Liu, Qian Xu, Vincent Wenchen Zheng, Hong Xue, ...
GECCO
2009
Springer
124views Optimization» more  GECCO 2009»
15 years 2 months ago
Reinforcement learning for games: failures and successes
We apply CMA-ES, an evolution strategy with covariance matrix adaptation, and TDL (Temporal Difference Learning) to reinforcement learning tasks. In both cases these algorithms se...
Wolfgang Konen, Thomas Bartz-Beielstein
ICML
2003
IEEE
15 years 10 months ago
Representational Issues in Meta-Learning
To address the problem of algorithm selection for the classification task, we equip a relational case base with new similarity measures that are able to cope with multirelational ...
Alexandros Kalousis, Melanie Hilario