Abstract This paper proposes an approach to continuously optimizing parallel scientific applications with dynamically changing architectures. We achieve this by combining a dynamic...
Solving multiagent planning problems modeled as DECPOMDPs is an important challenge. These models are often solved by using dynamic programming, but the high resource usage of cur...
Christopher Amato, Jilles Steeve Dibangoye, Shlomo...
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
—This paper is concerned with the representation and recognition of the observed dynamics (i.e., excluding purely spatial appearance cues) of spacetime texture based on a spatiot...
In this paper, we explore a hybrid global/local search optimization framework for dynamic voltage scaling in embedded multiprocessor systems. The problem is to find, for a multipr...