Sciweavers

185 search results - page 13 / 37
» Refining the Execution of Abstract Actions with Learned Acti...
Sort
View
92
Voted
JMLR
2010
107views more  JMLR 2010»
14 years 4 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
15 years 3 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
15 years 11 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
14 years 11 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»
14 years 9 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