Sciweavers

2950 search results - page 486 / 590
» Computing with Infinitely Many Processes
Sort
View
VLDB
2004
ACM
186views Database» more  VLDB 2004»
15 years 7 months ago
Indexing Large Human-Motion Databases
Data-driven animation has become the industry standard for computer games and many animated movies and special effects. In particular, motion capture data recorded from live actor...
Eamonn J. Keogh, Themis Palpanas, Victor B. Zordan...
IWANN
1999
Springer
15 years 6 months ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
R. Matthew Kretchmar, Charles W. Anderson
KES
1999
Springer
15 years 6 months ago
Dynamic Demes parallel genetic algorithm
Abstract—Dynamic Demes is a new method for the parallelisation of evolutionary algorithms. It was derived as a combination of two other parallelisation algorithms: the master-sla...
Mariusz Nowostawski, Riccardo Poli
TIME
1994
IEEE
15 years 6 months ago
An Algebraic Formulation of Temporal Knowledge for Reasoning about Recurring Events
We formulate an algebra of binary temporal relations between events the number of occurrences of which is unknown, but which are known to recur in time. Ontologically, we view the...
Robert A. Morris, William D. Shoaff, Lina Khatib
COOPIS
2004
IEEE
15 years 6 months ago
A Distributed and Parallel Component Architecture for Stream-Oriented Applications
Abstract. This paper introduces ThreadMill - a distributed and parallel component architecture for applications that process large volumes of streamed (time-sequenced) data, such a...
Paulo Barthelmess, Clarence A. Ellis