Probabilistic graphical models are used in a variety of domains to capture and represent general dependencies in joint probability distributions. In this document we examine the problem of learning the structure of an undirected graphical model, also called a Markov Random Field (MRF), given a set of independent and identically distributed (i.i.d.) samples. Specifically, we introduce an adaptive forward-backward greedy algorithm for learning the structure of a discrete, pairwise MRF given a high dimensional set of i.i.d. samples. The algorithm works by greedily estimating the neighborhood of each node independently through a series of forward and backward steps. By imposing a restricted strong convexity condition on the structure of the learned graph we show that the structure can be fully learned with high probability given $n=\Omega(d\log (p))$ samples where $d$ is the dimension of the graph and $p$ is the number of nodes. This is a significant improvement over existing convex-optimization based algorithms that require a sample complexity of $n=\Omega(d^2\log(p))$ and a stronger irrepresentability condition. We further support these claims with an empirical comparison of the greedy algorithm to node-wise $\ell_1$-regularized logistic regression as well as provide a real data analysis of the greedy algorithm using the Audioscrobbler music listener dataset. The results of this document provide an additional representation of work submitted by A. Jalali, C. Johnson, and P. Ravikumar to NIPS 2011. / text

This thesis makes contributions to the statistical research field of causal inference in observational studies. The results obtained are directly applicable in many scientific fields where effects of treatments are investigated and yet controlled experiments are difficult or impossible to implement. In the first paper we define a partially specified directed acyclic graph (DAG) describing the independence structure of the variables under study. Using the DAG we show that given that unconfoundedness holds we can use the observed data to select minimal sets of covariates to control for. General covariate selection algorithms are proposed to target the defined minimal subsets. The results of the first paper are generalized in Paper II to include the presence of unobserved covariates. Morevoer, the identification assumptions from the first paper are relaxed. To implement the covariate selection without parametric assumptions we propose in the third paper the use of a model-free variable selection method from the framework of sufficient dimension reduction. By simulation the performance of the proposed selection methods are investigated. Additionally, we study finite sample properties of treatment effect estimators based on the selected covariate sets. In paper IV we investigate misspecifications of parametric models of a scalar summary of the covariates, the propensity score. Motivated by common model specification strategies we describe misspecifications of parametric models for which unbiased estimators of the treatment effect are available. Consequences of the misspecification for the efficiency of treatment effect estimators are also studied.

This paper is an analysis of creative opportunities of graphical user interface software of computer mathematics systems. There were two computer mathematics systems chosen: Matlab 7, Maple 10 and Mathematica 5.2 for this work. In order to compare the creative opportunities of graphical user interface software in computer mathematics systems and universal programming languages, C++ Builder 6 system was chosen. In line, there were four application programs groups created in mathematics systems and in C++ Builder system. The process of creating these programs, the peculiarities of the codes and the final result were compared. To sum up, computer mathematics systems may be used for creating application programs. Classical programming tasks may be implemented in these programs. Moreover, computer mathematics systems used for creating software cannot be changed by any other program that needs classical programming constructions, analytic computations and creating of graphical user interface.

Today's high-throughput data collection devices, e.g. spectrometers and gene chips, create information in abundance. However, this poses serious statistical challenges, as the number of features is usually much larger than the number of observed units.  Further, in this high-dimensional setting, only a small fraction of the features are likely to be informative for any specific project. In this thesis, three different approaches to the two-class supervised classification in this high-dimensional, low sample setting are considered. There are classifiers that are known to mitigate the issues of high-dimensionality, e.g. distance-based classifiers such as Naive Bayes. However, these classifiers are often computationally intensive and therefore less time-consuming for discrete data. Hence, continuous features are often transformed into discrete features. In the first paper, a discretization algorithm suitable for high-dimensional data is suggested and compared with other discretization approaches. Further, the effect of discretization on misclassification probability in high-dimensional setting is evaluated.   Linear classifiers are more stable which motivate adjusting the linear discriminant procedure to high-dimensional setting. In the second paper, a two-stage estimation procedure of the inverse covariance matrix, applying Lasso-based regularization and Cuthill-McKee ordering is suggested. The estimation gives a block-diagonal approximation of the covariance matrix which in turn leads to an additive classifier. In the third paper, an asymptotic framework that represents sparse and weak block models is derived and a technique for block-wise feature selection is proposed.      Probabilistic classifiers have the advantage of providing the probability of membership in each class for new observations rather than simply assigning to a class. In the fourth paper, a method is developed for constructing a Bayesian predictive classifier. Given the block-diagonal covariance matrix, the resulting Bayesian predictive and marginal classifier provides an efficient solution to the high-dimensional problem by splitting it into smaller tractable problems. The relevance and benefits of the proposed methods are illustrated using both simulated and real data. / Med dagens teknik, till exempel spektrometer och genchips, alstras data i stora mängder. Detta överflöd av data är inte bara till fördel utan orsakar även vissa problem, vanligtvis är antalet variabler (p) betydligt fler än antalet observation (n). Detta ger så kallat högdimensionella data vilket kräver nya statistiska metoder, då de traditionella metoderna är utvecklade för den omvända situationen (p<n).  Dessutom är det vanligtvis väldigt få av alla dessa variabler som är relevanta för något givet projekt och styrkan på informationen hos de relevanta variablerna är ofta svag. Därav brukar denna typ av data benämnas som gles och svag (sparse and weak). Vanligtvis brukar identifiering av de relevanta variablerna liknas vid att hitta en nål i en höstack. Denna avhandling tar upp tre olika sätt att klassificera i denna typ av högdimensionella data.  Där klassificera innebär, att genom ha tillgång till ett dataset med både förklaringsvariabler och en utfallsvariabel, lära en funktion eller algoritm hur den skall kunna förutspå utfallsvariabeln baserat på endast förklaringsvariablerna. Den typ av riktiga data som används i avhandlingen är microarrays, det är cellprov som visar aktivitet hos generna i cellen. Målet med klassificeringen är att med hjälp av variationen i aktivitet hos de tusentals gener (förklaringsvariablerna) avgöra huruvida cellprovet kommer från cancervävnad eller normalvävnad (utfallsvariabeln). Det finns klassificeringsmetoder som kan hantera högdimensionella data men dessa är ofta beräkningsintensiva, därav fungera de ofta bättre för diskreta data. Genom att transformera kontinuerliga variabler till diskreta (diskretisera) kan beräkningstiden reduceras och göra klassificeringen mer effektiv. I avhandlingen studeras huruvida av diskretisering påverkar klassificeringens prediceringsnoggrannhet och en mycket effektiv diskretiseringsmetod för högdimensionella data föreslås. Linjära klassificeringsmetoder har fördelen att vara stabila. Nackdelen är att de kräver en inverterbar kovariansmatris och vilket kovariansmatrisen inte är för högdimensionella data. I avhandlingen föreslås ett sätt att skatta inversen för glesa kovariansmatriser med blockdiagonalmatris. Denna matris har dessutom fördelen att det leder till additiv klassificering vilket möjliggör att välja hela block av relevanta variabler. I avhandlingen presenteras även en metod för att identifiera och välja ut blocken. Det finns också probabilistiska klassificeringsmetoder som har fördelen att ge sannolikheten att tillhöra vardera av de möjliga utfallen för en observation, inte som de flesta andra klassificeringsmetoder som bara predicerar utfallet. I avhandlingen förslås en sådan Bayesiansk metod, givet den blockdiagonala matrisen och normalfördelade utfallsklasser. De i avhandlingen förslagna metodernas relevans och fördelar är visade genom att tillämpa dem på simulerade och riktiga högdimensionella data.

In the recent two years the analysis of principal and connective circuitry drawings proved that the principal and connective circuitries of very complicated projects are kept in a single file. Therefore, traditional specialized automated design system are not able to build and draw hybrid circuitries with the fragments of electromechanically networks together with the display of sensors and processors. The number of elements in such project files may reach from a few hundred until a few thousand. As this number is so high, the standard AutoCAD means do not quite fulfill the designers’ needs of working with blocks and their attributes. In this way they choose automated means that do not limit their abilities in preparing technical, assembly and tuning documentation, necessary for the completion of the projects. Therefore, based on the master’s paper, in order to fulfill the aforementioned needs, the building of the graphical data base block attribute system management system has been completed. The objective of the paper is the attributes and management of the graphical data base blocks. The purpose of the paper is to create a system of the graphical database attribute management and the means of using it. The purpose is defined by the following tasks: graphic data bases are analyzed; also the graphical data base blocks, their attributes, constituent parts and their management; the means of using the system in the medium of Auto CAD; based on the master’s paper the system of... [to full text]

Grafinių modelių projektavimas yra plačiai naudojamas tiek mokslo, tiek verslo srytyse. Pasaulyje naudojama įvairių kalbų, skirtų tiek sistemų architektūrų, tiek verslo procesų projektavimui. Daugumai kalbų yra sukurta įvairių įrankių, leidžiančių jų naudotojams projektuoti įvairius procesus ar statines sistemas. Vienai labiausiai paplitusių kalbų (UML) trūksta metodikos ir įrankių, gebančių korektiškai perteikti natūralia kalba sistemų architektų aprašytus grafinius modelius asmenims, mažai kvalifikuotiems grafinių modelių sudaryme, skaityme. Perteikimas tuo natūralesnis ir labiau suprantamesnis, kuo jis artimesnis natūraliai kalbai. Yra metodikų ir įrankių atliekančių grafinio modelio verbalizavimą, tačiau nėra koncentruotų ties diagramomis UML kalba, kurios geba formuoti ne tik statiką, bet ir dinamiką. Pagrindinis darbo tikslas yra sukurti metodiką ir realizuoti įrankį, kuris gebėtų grafinį modelį išreikštą UML kalba performuluoti natūralia kalba. / The graphical model architecture design is widely used for scientific and enterprise purposes. There are many languages concentrated on enterprise processes and static systems designing. One of the most popular modeling language (UML) is missing methodology and tools suitable for correct reformulation of graphical models (formulated by the UML) in natural language. The main purpose of the graphical model reformulation in natural language is to make models easier to understand for people whose are not specialized in UML. Methodology and tool which is capable of reformulating graphical models in natural language already exists, but it isn’t concentrated on UML or capable of reformulating static and dynamic processes. The main goal of this work is to define a methodology and implement a tool, which would be capable of translating the graphical UML model to a natural language text.

Darbe atlikta teorinė specialiosios ir bendrojo lavinimo mokyklos programų, gamtos mokslų mokymo metodų, organizavimo formų, bei vaizdinių gamtos mokymo priemonių analizė. Iškeltos hipotezės: kad gamtos dalyko pamokose panaudojus aktyviuosius mokymo metodus, susietus su grafinėmis užduotimis, mokinių žinios apie žinduolių klasę pagerės; kad temos „Žinduoliai“ turinio įsisavinimas geresnis, kai žinių įtvirtinimo užduotys ne vien tikrina ir įtvirtina žinias, bet ir sudaro galimybę pačiam atrasti atsakymą, tyrinėjant pateiktą naują mokomąją medžiagą. Organizuotas ugdomasis tyrimas, kurio tikslas - gerinti nežymiai protiškai atsilikusių mokinių žinių apie žinduolius įsisavinimą, remiantis moderniosios gamtos didaktikos siūlomais aktyviais mokymo metodais ir praktikos darbais (didelį dėmesį skiriant grafinių užduočių panaudojimui). Atlikta aprašomoji statistinė (vidurkių, procentų), kiekybinė ir kokybinė duomenų analizė. Tyrime dalyvavo 16 Klaipėdos 1 – osios ir 2 - osios specialiųjų mokyklų VIII klasės moksleivių. 10 gamtos dalyko mokytojų iš Klaipėdos, Rusnės bei Šiaulių specialiųjų mokyklų. Empirinėje dalyje nagrinėjamas mokytojų požiūris į gamtos dalyko mokymą, nežymiai protiškai atsilikusių mokinių žinios ir supratimas prieš temos „Žinduoliai“ mokymą, mokymo organizavimo specifika, moksleivių žinios ir supratimas po temos „Žinduoliai“ mokymo, gautų testų rezultatų po temos mokymo palyginimas. Svarbiausios empirinio tyrimo išvados: 1. Dauguma pedagogų žino apie... [toliau žr. visą tekstą] / The analysis of programmers of special and secondary schools, methods of natural sciences teaching, planning forms and visual teaching aids is carried out in this paper. The hypothesis: that pupils knowledge about mammalians will be improved using active teaching methods associated with graphical tasks during natural science lessons; that understanding of theme “Mammalians” is better when tasks for solidifying pupils knowledge are not used only for checking and solidifying, but gives the opportunity to learn themselves (find the answer) researching given material; that formed experimental teaching model will give enough good results for teaching theme “Mammalians” to narrowly mentally deficient pupils as well as for practice of natural sciences didactics. Organized educational research, the aim is to improve the knowledge of narrowly mentally deficient pupils about mammalians according to active methods recommended by modern science didactics and practical works (paying attention to usage of graphical tasks). Qualitative and quantitative analysis of data is done as well. Participants of the research are 16 8th form students of Klaipėda 1st and 2nd special boarding schools; 10 natural subject teachers from Klaipėda, Rusnė, Šilutė special schools. At the empirical part of work is analyzed teachers’ approach to natural subject teaching, knowledge of narrowly mentally deficient pupils before teaching theme “Mammalians”, specifics of teaching organization, knowledge of narrowly... [to full text]

Disertacijoje analizuojama, kokiomis sąlygomis nematomi žymenys atlieka pagrindinę prekių ženklo funkciją, t.y. atskiria vieno asmens prekes ir paslaugas nuo kito asmens prekių ir paslaugų. Atsakant į šį klausimą aptariamos pagrindinės kvapo, skonio ir garso charakteristikos, išskiriamos pagrindinės kvapo, skonio ir garso žymenų rūšys, identifikuojami nematomų žymenų funkcionalumo aspektai, identifikuojami pagrindiniai konkurenciniai aspektai, analizuojami išeikvojimo doktrinos taikymo ypatumai nematomų prekių ženklų atžvilgiu. Taip pat disertacijoje analizuojama nematomo žymens galimybės būti pavaizduotam grafiškai problematika. Aptariama grafinio pavaizdavimo reikalavimo esmė, paskirtis ir vieta absoliučių reikalavimų prekių ženklui sistemoje, analizuojami atskirų tipų nematomų žymenų grafinio pavaizdavimo ypatumai, atskirai aptariant šiuo metu žinomus nematomų žymenų grafinio pavaizdavimo metodus: žodinį žymenų aprašymą, cheminę formulę, nematomų žymenų pavyzdžių (angl. specimen) tinkamumą, atvaizdą, kvapo diagramas, kvepalų radarą, muzikinę penklinę ir garso diagramas. / This dissertation investigates the conditions under which a non-visible sign performs the primary function of a trade mark, i.e. to distinguish the goods or services of one undertaking from those of other undertakings. To answer this question, the dissertation identifies the main characteristics of smell, taste, and sound, the main types of smell, taste and sound signs, the functionality of non-visible signs, the main competitive aspects, and the peculiarities applying the depletion doctrine with respect to non-visible signs. The dissertation deals with the capability of a non-visible sign to be represented graphically. It describes the essence, purpose and role of the graphical representation requirement in the array of absolute requirements for a trade mark, also analyses the peculiarities of representation of different types of non-visible signs, by focusing more on graphical representation methods known today, such as verbal description of signs, chemical formula, relevance of specimen of non-visible signs, image, diagrams of smell, perfume radar, musical staves, and diagrams of sound.

Domain Specific Modeling (DSM) aims to increase productivity of software development by raising the level of abstraction beyond code concepts and using domain concepts. By providing a generative model-driven tooling component and runtime support, the Eclipse Graphical Modeling Framework (GMF) aims to simplify the creation of diagram editors for specific domains based on a series of model creation and transformation steps. GMF leverages the Eclipse Modeling Framework (EMF) and the Eclipse Graphical Editing Framework (GEF) to allow the graphical modeling of Domain Specific Languages (DSL). A Domain Specific Language (DSL) is developed specifically for a specific task and specific domain. In this research, the State Machine Compiler (SMC) represents the specific domain for which a DSL in a form of a diagram editor is developed using GMF. SMC is an open source Java tool allowing generation of state pattern classes from textual descriptions of state machines. The main objective of this research is to describe the use of GMF, highlight potential pitfalls and identify strengths and weaknesses of GMF based on certain criteria. To be able to feed the SMC diagrams created with the editor into SMC, a Java Emitter Templates (JET) transformation is used to transform SMC model instances into textual format expected by SMC. / Thesis (Master, Computing) -- Queen's University, 2011-04-14 18:58:08.797

No description available.