Sciweavers

2924 search results - page 554 / 585
» On the Use of Evidence in Neural Networks
Sort
View
ANOR
2010
130views more  ANOR 2010»
14 years 11 months ago
Greedy scheduling with custom-made objectives
We present a methodology to automatically generate an online job scheduling method for a custom-made objective and real workloads. The scheduling problem comprises independent para...
Carsten Franke, Joachim Lepping, Uwe Schwiegelshoh...
ANOR
2010
153views more  ANOR 2010»
14 years 11 months ago
Solving the Rectangular assignment problem and applications
The rectangular assignment problem is a generalization of the linear assignment problem (LAP): one wants to assign a number of persons to a smaller number of jobs, minimizing the ...
J. Bijsterbosch, A. Volgenant
CDC
2010
IEEE
196views Control Systems» more  CDC 2010»
14 years 8 months ago
Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
Vladislav B. Tadic
JMLR
2010
230views more  JMLR 2010»
14 years 8 months ago
Learning Dissimilarities for Categorical Symbols
In this paper we learn a dissimilarity measure for categorical data, for effective classification of the data points. Each categorical feature (with values taken from a finite set...
Jierui Xie, Boleslaw K. Szymanski, Mohammed J. Zak...
CISIS
2011
IEEE
14 years 1 months ago
Improving Scheduling Techniques in Heterogeneous Systems with Dynamic, On-Line Optimisations
—Computational performance increasingly depends on parallelism, and many systems rely on heterogeneous resources such as GPUs and FPGAs to accelerate computationally intensive ap...
Marcin Bogdanski, Peter R. Lewis, Tobias Becker, X...