Sciweavers

4035 search results - page 13 / 807
» Useless Actions Are Useful
Sort
View
NIPS
2004
13 years 8 months ago
Active Learning for Anomaly and Rare-Category Detection
We introduce a novel active-learning scenario in which a user wants to work with a learning algorithm to identify useful anomalies. These are distinguished from the traditional st...
Dan Pelleg, Andrew W. Moore
ICML
2002
IEEE
14 years 8 months ago
Action Refinement in Reinforcement Learning by Probability Smoothing
In many reinforcement learning applications, the set of possible actions can be partitioned by the programmer into subsets of similar actions. This paper presents a technique for ...
Carles Sierra, Dídac Busquets, Ramon L&oacu...
FGCN
2008
IEEE
175views Communications» more  FGCN 2008»
14 years 1 months ago
Environment Recognition Based on Human Actions Using Probability Networks
To realize context aware applications for smart home environments, it is necessary to recognize function or usage of objects as well as categories of them. On conventional researc...
Hiroshi Miki, Atsuhiro Kojima, Koichi Kise
IVC
2006
113views more  IVC 2006»
13 years 7 months ago
Minimal-latency human action recognition using reliable-inference
We present a probabilistic reliable-inference framework to address the issue of rapid detection of human actions with low error rates. The approach determines the shortest video e...
James W. Davis, Ambrish Tyagi
IJCAI
2003
13 years 8 months ago
Action Selection for Single- and Multi-Robot Tasks Using Cooperative Extended Kohonen Maps
This paper presents an action selection framework based on an assemblage of self-organizing neural networks called Cooperative Extended Kohonen Maps. This framework encapsulates t...
Kian Hsiang Low, Wee Kheng Leow, Marcelo H. Ang Jr...