Sciweavers

185 search results - page 13 / 37
» Refining the Execution of Abstract Actions with Learned Acti...
Sort
View
JMLR
2010
107views more  JMLR 2010»
13 years 2 months ago
Modeling Knowledge Worker Activity
This paper describes an approach to constructing a probabilistic process model representing knowledge worker activity out of a log of primitive events, such as e-mails, web page v...
Tadej Stajner, Dunja Mladenic
FDL
2005
IEEE
14 years 1 months ago
Synthesis for Unified Control- and Data-Oriented Models
In the Software/Hardware Engineering model-driven design methodology, preservation of real-time system properties can be guaranteed in the model synthesis up to a small time-deviat...
Oana Florescu, Jeroen Voeten, Henk Corporaal
CVPR
2006
IEEE
14 years 9 months ago
The Function Space of an Activity
An activity consists of an actor performing a series of actions in a pre-defined temporal order. An action is an individual atomic unit of an activity. Different instances of the ...
Ashok Veeraraghavan, Amit K. Roy Chowdhury
SCAI
2008
13 years 8 months ago
Fast Learning in an Actor-Critic Architecture with Reward and Punishment
Abstract. A reinforcement architecture is introduced that consists of three complementary learning systems with different generalization abilities. The ACTOR learns state-action as...
Christian Balkenius, Stefan Winberg
ECEASST
2008
77views more  ECEASST 2008»
13 years 7 months ago
Using OCL in Executable UML
Executable UML allows precisely describing the software system at level of abstraction. The executable models can be translated to a less programming language completely or execute...
Ke Jiang, Lei Zhang, Shigeru Miyake