Sciweavers

911 search results - page 118 / 183
» Combining programs and state machines
Sort
View
ECML
2007
Springer
14 years 2 months ago
Policy Gradient Critics
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
Daan Wierstra, Jürgen Schmidhuber
PAAPP
2007
115views more  PAAPP 2007»
13 years 8 months ago
Quantum computing: beyond the limits of conventional computation
The quantum model of computation not only o ers entirely new ways to manipulate information, but also allows information processing tasks to be formulated in unconventional, genui...
Marius Nagy, Selim G. Akl
ISVC
2010
Springer
13 years 7 months ago
Automatic Learning of Gesture Recognition Model Using SOM and SVM
In this paper, we propose an automatic learning method for gesture recognition. We combine two different pattern recognition techniques: the SelfOrganizing Map (SOM) and Support Ve...
Masaki Oshita, Takefumi Matsunaga
ICPADS
2010
IEEE
13 years 6 months ago
Data-Aware Task Scheduling on Multi-accelerator Based Platforms
To fully tap into the potential of heterogeneous machines composed of multicore processors and multiple accelerators, simple offloading approaches in which the main trunk of the ap...
Cédric Augonnet, Jérôme Clet-O...
ASM
2008
ASM
13 years 10 months ago
Modeling Workflows, Interaction Patterns, Web Services and Business Processes: The ASM-Based Approach
Abstract. We survey the use of the Abstract State Machines (ASM) method for a rigorous foundation of modeling and validating web services, workflows, interaction patterns and busin...
Egon Börger, Bernhard Thalheim