This paper describes a parallel algorithm for selecting activation functionsof an articial network. For checking the eciency of this algorithm a count ofmultiplicative and additive operations is used.[...]

In diesem Arbeitsbericht werden zuvor nicht identizierte Bedrohungenbezüglich des Wahlgeheimnisses des in [BKG11] vorgeschlagenen Konzepteszur Authentizierung von Wählern bei elektronischen Wahlen mittelsdes neuen Personalausweises aufgezeigt. Überdies wird mit der Einführungeiner...

We present a non-linear camera pose estimator, which is able to handle a combined input of point and line featurecorrespondences. For three or more correspondences, the estimator works on any arbitrary number and choiceof the feature type, which provides an estimation of the pose on a preferably...

The paper is devoted to solving the problem of assessing the quality of the medicalelectronic service. A variety of dimensions and factors of quality, methods and models applied indifferent scopes of activity for assessing quality of service is researched. The basic aspects,requirements and...

This paper describes the analysis of a neural network used to predict currencyexchange rates in comparison to technical analysis. The neural network structuresused are a multilayer perceptron and a Volterra network.[...]

The paper is devoted to solving a problem of the development of the website of Russianmunicipal policlinics and provides a selection of a set of elements which should be posted on awebsite. Such elements are necessary to provide citizens with correct and ergonomic e-services.The insufficient...

This paper describes parallel algorithms for training articial neural networks.Possible levels of parallelity are presented. Experiments for checking the efficiencyof algorithms are discussed.[...]

The estimation of various social objects is necessary in different fields of social life, science,education, etc. This estimation is usually used for forecasting, for evaluating of different propertiesand for other goals in complex man-machine systems.[...]

This paper has a twofold concern. First, to show that probabilitypropagation nets (PPNs) can be derived from formulae for conditionalprobabilities. Second, to show that PPNs are usable for (local)propagations of mass distributions, too, if the inscriptions are suitablyadapted.[...]

Knowledge compilation is a common technique for propositionallogic knowledge bases. A given knowledge base is transformedinto a normal form, for which queries can be answered efficiently. Thisprecompilation step is expensive, but it only has to be performed once.We apply this technique to...