Матричные уравнения локального логико-вероятностного вывода оценок истинности элементов в алгебраических байесовских сетях
The processing of probabilistically uncertain knowledge patterns in intellectual decision support systems falls into three kinds of probabilistic-logic inference, such as reconciliation, a priori and a posteriori inference. The paper presents formulae that allow for putting the process down in terms of matrix-vector language.
We suggest an econometric model of probability of default based on regular financial disclosures of Russian banks. We also suggest a quantization of the continuous explanatory variables that allows to account for non-linear effects and to achieve superior accuracy compared with regression tree and Bayesian network models estimated over the same sample. The econometric estimates of probability of default are broadly consistent with the historical default frequencies of rated obligors and risk-neutral probabilities of default inferred from credit spreads in a reduced-form model.
This book constitutes the refereed proceedings of the 10th International Conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2014, held in St. Petersburg, Russia in July 2014. The 40 full papers presented were carefully reviewed and selected from 128 submissions. The topics range from theoretical topics for classification, clustering, association rule and pattern mining to specific data mining methods for the different multimedia data types such as image mining, text mining, video mining and Web mining.
The present manual is written on the basis of the course on inductive logic which is delivered in English to philosophy students of National Research University Higher School of Economics. The manual describes the main approaches to constructing inductive logic; it clarifies its key notions and rules, and it formulates its major problems. This introductory text can be useful for all readers who are interested in contemporary inductive logic.
A collection of TU games solutions intermediate between the prekernel and the prenucleolus is considered. All these solutions are Davis-Maschler consistent, symmetric and covariant. Each solution from the collection is parametrized by a positive integer k such that for all games with the number of players not greater than k, the solution for parameter k coincides with the prenucleolus, and for games with more than k players it is maximal, i.e. it satisfies the "k-converse consistency". The properties of solutions are described and their characterization in terms of balancedness is given.
Inconsistency of business processes can affect company profits and lead to the loss of regular customers and reputation in the market. Well managed business process has one key distinctive feature – a consistency. Checking the consistency of business process helps to reveal hidden bugs in the process model, but requires considerable labor costs and analytics. We compared two approaches to verifying consistency. The first approach is based on generating object life cycles for each object type used in process and supported by special tool as an extension for IBM WebSphere Business Modeler. Another one is a proposition to use DEMO methodology for verifying consistency. The results of research show that DEMO methodology enables significantly reduce labor costs and improve quality of analyze
The paper describe key points in algebraic bayesian network knowledge pattern implementation on C++ programming language. Knowledge pattern implemented as class that handle and store estimation for knowledge pattern elements. It also provide a couple of methods for processing knowledge pattern such as consistency update and a posteriori inference.
Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variational inference, which struggle in the full parameter space. We show that Bayesian model averaging over the induced posterior in these subspaces produces accurate predictions and well-calibrated predictive uncertainty for both regression and image classification.
We consider certain spaces of functions on the circle, which naturally appear in harmonic analysis, and superposition operators on these spaces. We study the following question: which functions have the property that each their superposition with a homeomorphism of the circle belongs to a given space? We also study the multidimensional case.
We consider the spaces of functions on the m-dimensional torus, whose Fourier transform is p -summable. We obtain estimates for the norms of the exponential functions deformed by a C1 -smooth phase. The results generalize to the multidimensional case the one-dimensional results obtained by the author earlier in “Quantitative estimates in the Beurling—Helson theorem”, Sbornik: Mathematics, 201:12 (2010), 1811 – 1836.
We consider the spaces of function on the circle whose Fourier transform is p-summable. We obtain estimates for the norms of exponential functions deformed by a C1 -smooth phase.
This proceedings publication is a compilation of selected contributions from the “Third International Conference on the Dynamics of Information Systems” which took place at the University of Florida, Gainesville, February 16–18, 2011. The purpose of this conference was to bring together scientists and engineers from industry, government, and academia in order to exchange new discoveries and results in a broad range of topics relevant to the theory and practice of dynamics of information systems. Dynamics of Information Systems: Mathematical Foundation presents state-of-the art research and is intended for graduate students and researchers interested in some of the most recent discoveries in information theory and dynamical systems. Scientists in other disciplines may also benefit from the applications of new developments to their own area of study.