Sciweavers

4894 search results - page 971 / 979
» Dynamic Abstraction Planning
Sort
View
TNN
1998
125views more  TNN 1998»
14 years 11 months ago
Symbolic connectionism in natural language disambiguation
Abstract—Natural language understanding involves the simultaneous consideration of a large number of different sources of information. Traditional methods employed in language an...
Samuel W. K. Chan, James Franklin
PAMI
2007
186views more  PAMI 2007»
14 years 10 months ago
Value-Directed Human Behavior Analysis from Video Using Partially Observable Markov Decision Processes
—This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the co...
Jesse Hoey, James J. Little
ICRA
2010
IEEE
158views Robotics» more  ICRA 2010»
14 years 9 months ago
Movement templates for learning of hitting and batting
Abstract— Hitting and batting tasks, such as tennis forehands, ping-pong strokes, or baseball batting, depend on predictions where the ball can be intercepted and how it can prop...
Jens Kober, Katharina Mülling, Oliver Kroemer...
INFOCOM
2010
IEEE
14 years 9 months ago
Energy-Conserving Scheduling in Multi-hop Wireless Networks with Time-Varying Channels
Abstract— MaxWeight algorithm, a.k.a., back-pressure algorithm, has received much attention as a viable solution for dynamic link scheduling in multi-hop wireless networks. The b...
Yang Song, Chi Zhang, Yuguang Fang, Zhisheng Niu
JFP
2010
107views more  JFP 2010»
14 years 9 months ago
Lightweight checkpointing for concurrent ML
Transient faults that arise in large-scale software systems can often be repaired by re-executing the code in which they occur. Ascribing a meaningful semantics for safe re-execut...
Lukasz Ziarek, Suresh Jagannathan