Thesis (Ph. D.)--Rutgers University, 2007. / "Graduate Program in Computer Science." Includes bibliographical references (p. 284-290).

No description available.

Software systems will eventually contribute to their own maintenance using implementations of self-awareness. Understanding how to specify, model, and implement software with a sense of self is a daunting problem. This research draws inspiration from the automatic functioning of a gimbal---a self-righting mechanical device that supports an object and maintains the orientation of this object with respect to gravity independently of its immediate operating environment. A software gimbal exhibits a self-righting feature that provisions software with two auxiliary mechanisms: a historical mechanism and a reflective mechanism. The historical mechanism consists of behavior classifiers trained on statistical models of data that are collected from executions of the program that exhibit known behaviors of the program. The reflective mechanism uses the historical mechanism to assess an ongoing or selected execution. This dissertation presents techniques for the identification and modeling of program execution features as statistical models. It further demonstrates how statistical machine-learning techniques can be used to manipulate these models and to construct behavior classifiers that can automatically detect and label known program behaviors and detect new unknown behaviors. The thesis is that statistical summaries of data collected from a software program's executions can model and predict external behaviors of the program. This dissertation presents three control-flow features and one value-flow feature of program executions that can be modeled as stochastic processes exhibiting the Markov property. A technique for building automated behavior classifiers from these models is detailed. Empirical studies demonstrating the efficacy of this approach are presented. The use of these techniques in example software engineering applications in the categories of software testing and failure detection are described.

Thesis (Ph. D.)--Rutgers University, 2009. / "Graduate Program in Computer Science." Includes bibliographical references (p. 238-261).

In the last decade Support Vector Machines (SVMs) have emerged as an important learning technique for solving classification and regression problems in various fields, most notably in computational biology, finance and text categorization. This is due in part to built-in mechanisms to ensure good generalization which leads to accurate prediction, the use of kernel functions to model non-linear distributions, the ability to train relatively quickly on large data sets using novel mathematical optimization techniques and most significantly the possibility of theoretical analysis using computational learning theory. In this thesis, we discuss the theoretical basis and computational approaches to Support Vector Machines.

Thesis (Ph. D.)--University of Washington, 2007. / Includes bibliographical references (p. 134-142).

Thesis (Ph.D.)--City University of Hong Kong, 2009. / "Submitted to Department of Mathematics in partial fulfillment of the requirements for the degree of Doctor of Philosophy." Includes bibliographical references (leaves [57]-62)

Thesis (Ph. D.)--University of British Columbia, 2000. / Description based on contents viewed Aug. 16, 2007; title from title screen. Includes bibliographical references (p. 153-157).

A central goal of theoretical computer science is to characterize the limits of efficient computation in a variety of models. We pursue this research objective in the contexts of communication complexity and computational learning theory. In the former case, one seeks to understand which distributed computations require a significant amount of communication among the parties involved. In the latter case, one aims to rigorously explain why computers cannot master some prediction tasks or learn from past experience. While communication and learning may seem to have little in common, they turn out to be closely related, and much insight into both can be gained by studying them jointly. Such is the approach pursued in this thesis. We answer several fundamental questions in communication complexity and learning theory and in so doing discover new relations between the two topics. A consistent theme in our work is the use of analytic methods to solve the problems at hand, such as approximation theory, Fourier analysis, matrix analysis, and duality. We contribute a novel technique, the pattern matrix method, for proving lower bounds on communication. Using our method, we solve an open problem due to Krause and Pudlák (1997) on the comparative power of two well-studied circuit classes: majority circuits and constant-depth AND/OR/NOT circuits. Next, we prove that the pattern matrix method applies not only to classical communication but also to the more powerful quantum model. In particular, we contribute lower bounds for a new class of quantum communication problems, broadly subsuming the celebrated work by Razborov (2002) who used different techniques. In addition, our method has enabled considerable progress by a number of researchers in the area of multiparty communication. Second, we study unbounded-error communication, a natural model with applications to matrix analysis, circuit complexity, and learning. We obtain essentially optimal lower bounds for all symmetric functions, giving the first strong results for unbounded-error communication in years. Next, we resolve a longstanding open problem due to Babai, Frankl, and Simon (1986) on the comparative power of unbounded-error communication and alternation, showing that [mathematical equation]. The latter result also yields an unconditional, exponential lower bound for learning DNF formulas by a large class of algorithms, which explains why this central problem in computational learning theory remains open after more than 20 years of research. We establish the computational intractability of learning intersections of halfspaces, a major unresolved challenge in computational learning theory. Specifically, we obtain the first exponential, near-optimal lower bounds for the learning complexity of this problem in Kearns’ statistical query model, Valiant’s PAC model (under standard cryptographic assumptions), and various analytic models. We also prove that the intersection of even two halfspaces on {0,1}n cannot be sign-represented by a polynomial of degree less than [Theta](square root of n), which is an exponential improvement on previous lower bounds and solves an open problem due to Klivans (2002). We fully determine the relations and gaps among three key complexity measures of a communication problem: product discrepancy, sign-rank, and discrepancy. As an application, we solve an open problem due to Kushilevitz and Nisan (1997) on distributional complexity under product versus nonproduct distributions, as well as separate the communication classes PPcc and UPPcc due to Babai, Frankl, and Simon (1986). We give interpretations of our results in purely learning-theoretic terms. / text

A Inteligência Artificial atualmente é um vasto campo de pesquisa. Existem diversas técnicas sendo pesquisadas, sendo que nesta tese foram utilizadas a Teoria Fuzzy, Árvores de Decisão e Redes Neurais. As três técnicas têm sido empregadas com sucesso nas mais diversas aplicações nas áreas de automação e controle, reconhecimento de padrões, reconhecimento de voz, detecção de falhas e classificação, entre outras. A Teoria Fuzzy permite trabalhar com as incertezas e provê um entendimento simbólico para compreensão do conhecimento. As Árvores de Decisão têm capacidade de construir decisões simbólicas para a classificação de problemas e, através do conhecimento obtido, pode-se construir regras simbólicas para uma tomada de decisão. A Teoria Fuzzy também pode ser incorporada às árvores de decisão, aumentando seu poder de representação e aplicabilidade. As Redes Neurais (algoritmo back-propagation) têm apresentado ótimos resultados na aprendizagem de funções e em problemas de classificação. A contribuição desta tese é mostrar a aplicação das três técnicas de Inteligência Artificial (IA) em processos de fabricação de Vidro. Os processos de fabricação do vidro foram analisados e a proposta da tese é a aplicação das técnicas de IA nas fábricas de produção de vidros para embalagens e vidros planos. Na primeira fábrica aplicam-se as técnicas de IA para classificar os defeitos que ocorrem no Vidro para Embalagens, em função das condições operacionais dos fornos de fusão. Na segunda fábrica aplicam-se as técnicas para classificar os defeitos em função das matérias primas utilizadas na produção do vidro. Na terceira fábrica as técnicas são aplicadas na classificação dos padrões de fabricação do vidro plano. Os resultados obtidos com a classificação de defeitos e padrões foram de maneira geral satisfatórios. As três técnicas de IA apresentadas foram utilizadas para a análise das bases de dados nas três fábricas de vidro estudadas nesta tese. As técnicas de IA obtiveram classificações satisfatórias para os defeitos do vidro para embalagens e para classificar os padrões dos vidros planos. Os resultados obtidos a partir das técnicas são comparados e apresentam resultados promissores. / The Artificial Intelligence now is a vast research field. There are several techniques exist being researched. In this thesis Fuzzy Theory, Decision Trees and Neural Networks were used. The three techniques have been successfully applied in several applications in the areas of automation and control, pattern recognition, voice recognition, detection of flaws and classification, among others. The Fuzzy Theory allows to work with the uncertainties and they provide a symbolic understanding for understanding of the knowledge. The Decision Trees have capacity to build symbolic decisions for the classification of problems and through the knowledge obtained by the tree could be built symbolic rules for a socket of decision. The Fuzzy Theory can also be incorporate them tree of decision increasing the representation power and applicability of the Decision trees. Neural Networks (algorithm back-propagation) it has been presenting great results in the learning of functions and in classification problems. The contribution of this thesis is to show the application of the three techniques of Artificial Intelligence (AI) in processes of production of Glass. The processes of production of the glass were analyzed and the proposal of the thesis is the application of the techniques of AI in the factories of production of glasses to packings and plane glasses. In the first factory it is applied the techniques of AI to classify the defects that happen in the Glass for Packings in function of the operational conditions of the coalition ovens. In the second factory it is applied the techniques to classify the defects in the matters cousins\' function used in the production of the glass. In the third factory the techniques are applied in the classification of the patterns of production of the plane glass. The results obtained with the classification of defects and patterns were in a satisfactory general way. The three techniques of AI presented were used for the analysis of the bases of data in the three glass factories studied in thesis. The techniques of AI obtained a satisfactory classification for the defects of the glass for packings and for the patterns of the plane glasses. The results obtained starting from the techniques are compared and they present promising results.