Sciweavers

2363 search results - page 108 / 473
» Learning Algorithms for Domain Adaptation
Sort
View
ECML
2006
Springer
15 years 10 months ago
Scaling Model-Based Average-Reward Reinforcement Learning for Product Delivery
Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity. We present approaches that ...
Scott Proper, Prasad Tadepalli
ICMCS
2006
IEEE
143views Multimedia» more  ICMCS 2006»
16 years 10 days ago
Person Tracking in Smart Rooms using Dynamic Programming and Adaptive Subspace Learning
We present a robust vision system for single person tracking inside a smart room using multiple synchronized, calibrated, stationary cameras. The system consists of two main compo...
ZhenQiu Zhang, Gerasimos Potamianos, Stephen M. Ch...
CVPR
2010
IEEE
15 years 11 months ago
Adaptive Generic Learning for Face Recognition from a Single Sample per Person
Real-world face recognition systems often have to face the single sample per person (SSPP) problem, that is, only a single training sample for each person is enrolled in the datab...
Yu Su, Shiguang Shan, Xilin Chen, wen Gao
ALT
2008
Springer
16 years 3 months ago
A Uniform Lower Error Bound for Half-Space Learning
Abstract. We give a lower bound for the error of any unitarily invariant algorithm learning half-spaces against the uniform or related distributions on the unit sphere. The bound i...
Andreas Maurer, Massimiliano Pontil
ATAL
2003
Springer
15 years 11 months ago
How to calm hyperactive agents
System performance in multi-agent resource allocation systems can often improve if individual agents reduce their activity. Agents in such systems need a way to modulate their ind...
H. Van Dyke Parunak, Sven Brueckner, Robert S. Mat...