Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
We derive PAC-Bayesian generalization bounds for supervised and unsupervised learning models based on clustering, such as co-clustering, matrix tri-factorization, graphical models...
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
For wireless mobile Internet users the length of the battery life is one of the most important performance factors. The energy efficiency of the data transmission over radio is a ...
Enrico Rantala, Arto Karppanen, Seppo Granlund, Pa...
This paper proposes the modeling of technical systems and their behavior by means of Unified Modeling Language (UML) State Machines and the extending UML Profile for Schedulabil...