Informatica

The sample-based rule obtained from Bayes classification rule by replacing unknown parameters by ML estimates from stratified training sample is used for classification of random observations into one of two widely applicable Gamma distributions. The first order asymptotic expansions of the expected risk regret for different parametric structure cases are derived. These are used to evaluate performance of the proposed classification rule and to find the optimal training sample allocation minimizing the asymptotic expected risk regret.

Comparative study of the recognition of nonsemantic geometrical figures by the human subjects and ART neural network was carried out. The results of computer simulation experiments with ART neural network showed well correspondence with the psychophysical data on the recognition of different complexity visual patterns: in both cases the patterns of medium complexity were recognized with the highest accuracy. On the contrary, the recognition of the patterns by their informative fragments demonstrated different recognition strategies employed by natural and artificial neural systems. For biological systems, it is necessary the presence of not only distinctive features in visual patterns but the redundant features as well for successive recognition. ART neural network ignores redundant features and recognizes visual patterns with equal accuracy whether the whole pattern or only the informative fragment of any completeness is present.

Principles of the framework called time series forecasting automation are presented. It is required in processing massive temporal data sets and creating completely user-oriented forecasting software where manual data analysis and a user's decision-making is either impractical or undesirable. Its distinct features are local extrapolation models, their active training, criterion of model performance assessment used in adding new examples to the model training set and in deciding on which one of a group of competing models consistent with the common training set performs best. A generalized algorithm for local model tuning on massive data series that can be run without human intervention is presented.

This paper presents a parallel version of a Generalized Conjugate Gradient algorithm proposed by Liu and Story in which the search direction considers the effect of the inexact line search. We describe the implementation of this algorithm on a parallel architecture and analyze the related speedup ratios. Numerical results are given for a shared memory computer (Cray C92).

Language engineering encompassing natural language processing and speech processing became very important for a development of every nation in multilingual Europe. After the Council of European Union approved conclucions on linguistic and cultural diversity, tools and systems created for every European language are necessary to overcome language barriers and to use all languages in various spheres of human cooperation. The paper gives an overview and a consideration of language engineering in Lithuania.

Analysis of work of art may be treated as some sort of classification of information: does the work is really artistic or not. This article is an attempt to introduce some classification criteria, though the author understands that the problem is extremely delicate and complicated. Attractiveness of work of art is determined by its proportions. The screen of a computer by itself is a mechanism for arranging proportions, however it is not able to resolve the problem of proportions completely. By starting with the horizontal (or vertical), which touches the main element of the picture, a grid can be constructed. Other elements of the picture become interlocked with the grid. In this paper, a method of construction of proportional grids, which can serve as an implement to creation of art or as criterion of coherence, artistic value and style of works of art, is proposed. Variety of proportional grids can be great, and we can create its from grids of coordinated geometrical forms.

The object of the present paper is to study certain subclasses Jp^* (a,b,σ) and Cp(a,b,σ) of analytic p-valent functions, and obtain coefficient bounds and distortion properties for functions belonging to these subclasses. Further results include distortion inequalities and radii of close-to-convexity, starlikeness and convexity for these classes of functions.

This article gives ideas for developing statistics software which can work without user intervention. Some popular methods of bandwidth selection for kernel density estimation (the nearest neighbour, least squares cross-validation, “plug-in” technique) are discussed. Modifications of the cross-validation criterion are proposed. Two-stage estimators combining these methods with multiplicative bias correction are investigated by simulation means.

This paper describes a method how to represent and build a reusable VHDL component. By that component we can, for example, describe a family of the relative VHDL models. To represent the component, we use external functions as a mechanism to support a pre-processing and perform the instantiation of the component. A user interface, the constituent of the reusable component, serves for transferring parameters for the instantiation. We deliver a formal syntax of the functions and examples of their semantics. We describe the design of the reusable component as a procedure of transferring of: a) the intrinsic characteristics for a given family of domain objects and b) features from a given VHDL model(s). Those features require to be re-coded and extended with new ones by means of the external functions introduced. To test a reusable component, we use pre-processing and modelling.