Effective and efficient mapping algorithms for multisite parallel applications are fundamental to exploit the potentials of grid computing. Since the problem of optimally mapping i...
Ivanoe De Falco, Antonio Della Cioppa, Umberto Sca...
Abstract This paper proposes an approach to continuously optimizing parallel scientific applications with dynamically changing architectures. We achieve this by combining a dynamic...
Map- and fold-like skeletons are a suitable abstractions to guide parallel program execution in functional array processing. However, when it comes to achieving high performance, i...
Thinning operation is a fundamental operation in image processing. It is a typical preprocessing stage for pattern recognition and data compression. In this report we proposed an ...
Abstract. A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization met...
Georg Schneider, Heiko Wersing, Bernhard Sendhoff,...