This research identifies and investigates major issues in inducing accurate and comprehensible fuzzy rules from datasets. A review of the current literature on fuzzy rulebase induction uncovers two significant issues: A. There is a tradeoff between inducing accurate fuzzy rules and inducing comprehensible fuzzy rules; and, B. A common strategy for the induction of fuzzy rulebases, that of iterative rule learning where the rules are generated one by one and independently of each other, may not be an optimal one. FRANTIC, a system that provides a framework for exploring the claims above is developed. At the core lies a mechanism for creating individual fuzzy rules. This is based on a significantly modified social insect-inspired heuristic for combinatorial optimisation -- Ant Colony Optimisation. The rule discovery mechanism is utilised in two very different strategies for the induction of a complete fuzzy rulebase: 1. The first follows the common iterative rule learning approach for the induction of crisp and fuzzy rules; 2. The second has been designed during this research explicitly for the induction of a fuzzy rulebase, and generates all rules in parallel. Both strategies have been tested on a number of classification problems, including medical diagnosis and industrial plant fault detection, and compared against other crisp or fuzzy induction algorithms that use more well-established approaches. The results challenge statement A above, by presenting evidence to show that one criterion need not be met at the expense of the other. This research also uncovers the cost that is paid -- that of computational expenditure -- and makes concrete suggestions on how this may be resolved. With regards to statement B, until now little or no evidence has been put forward to support or disprove the claim. The results of this research indicate that definite advantages are offered by the second simultaneous strategy, that are not offered by the iterative one. These benefits include improved accuracy over a wide range of values for several key system parameters. However, both approaches also fare well when compared to other learning algorithms. This latter fact is due to the rule discovery mechanism itself -- the adapted Ant Colony Optimisation algorithm -- which affords several additional advantages. These include a simple mechanism within the rule construction process that enables it to cope with datasets that have an imbalanced distribution between the classes, and another for controlling the amount of fit to the training data. In addition, several system parameters have been designed to be semi-autonomous so as to avoid unnecessary user intervention, and in future work the social insect metaphor may be exploited and extended further to enable it to deal with industrial-strength data mining issues involving large volumes of data, and distributed and/or heterogeneous databases.

Algoritmos de aprendizado de máquina são frequentemente os mais indicados em uma grande variedade de aplicações de mineração dados. Entretanto, a maioria das pesquisas em aprendizado de máquina refere-se ao problema bem definido de encontrar um modelo (geralmente de classificação) de um conjunto de dados pequeno, relativamente bem preparado para o aprendizado, no formato atributo-valor, no qual os atributos foram previamente selecionados para facilitar o aprendizado. Além disso, o objetivo a ser alcançado é simples e bem definido (modelos de classificação precisos, no caso de problemas de classificação). Mineração de dados propicia novas direções para pesquisas em aprendizado de máquina e impõe novas necessidades para outras. Com a mineração de dados, algoritmos de aprendizado estão quebrando as restrições descritas anteriormente. Dessa maneira, a grande contribuição da área de aprendizado de máquina para a mineração de dados é retribuída pelo efeito inovador que a mineração de dados provoca em aprendizado de máquina. Nesta tese, exploramos alguns desses problemas que surgiram (ou reaparecem) com o uso de algoritmos de aprendizado de máquina para mineração de dados. Mais especificamente, nos concentramos seguintes problemas: Novas abordagens para a geração de regras. Dentro dessa categoria, propomos dois novos métodos para o aprendizado de regras. No primeiro, propomos um novo método para gerar regras de exceção a partir de regras gerais. No segundo, propomos um algoritmo para a seleção de regras denominado Roccer. Esse algoritmo é baseado na análise ROC. Regras provêm de um grande conjunto externo de regras e o algoritmo proposto seleciona regras baseado na região convexa do gráfico ROC. Proporção de exemplos entre as classes. Investigamos vários aspectos relacionados a esse tópico. Primeiramente, realizamos uma série de experimentos em conjuntos de dados artificiais com o objetivo de testar nossa hipótese de que o grau de sobreposição entre as classes é um fator complicante em conjuntos de dados muito desbalanceados. Também executamos uma extensa análise experimental com vários métodos (alguns deles propostos neste trabalho) para balancear artificialmente conjuntos de dados desbalanceados. Finalmente, investigamos o relacionamento entre classes desbalanceadas e pequenos disjuntos, e a influência da proporção de classes no processo de rotulação de exemplos no algoritmo de aprendizado de máquina semi-supervisionado Co-training. Novo método para a combinação de rankings. Propomos um novo método, chamado BordaRank, para construir ensembles de rankings baseado no método de votação borda count. BordaRank pode ser aplicado em qualquer problema de ordenação binária no qual vários rankings estejam disponíveis. Resultados experimentais mostram uma melhora no desempenho com relação aos rankings individuais, alem de um desempenho comparável com algoritmos mais sofisticados que utilizam a predição numérica, e não rankings, para a criação de ensembles para o problema de ordenação binária. / Machine learning algorithms are often the most appropriate algorithms for a great variety of data mining applications. However, most machine learning research to date has mainly dealt with the well-circumscribed problem of finding a model (generally a classifier) given a single, small and relatively clean dataset in the attribute-value form, where the attributes have previously been chosen to facilitate learning. Furthermore, the end-goal is simple and well-defined, such as accurate classifiers in the classification problem. Data mining opens up new directions for machine learning research, and lends new urgency to others. With data mining, machine learning is now removing each one of these constraints. Therefore, machine learning's many valuable contributions to data mining are reciprocated by the latter's invigorating effect on it. In this thesis, we explore this interaction by proposing new solutions to some problems due to the application of machine learning algorithms to data mining applications. More specifically, we contribute to the following problems. New approaches to rule learning. In this category, we propose two new methods for rule learning. In the first one, we propose a new method for finding exceptions to general rules. The second one is a rule selection algorithm based on the ROC graph. Rules come from an external larger set of rules and the algorithm performs a selection step based on the current convex hull in the ROC graph. Proportion of examples among classes. We investigated several aspects related to this issue. Firstly, we carried out a series of experiments on artificial data sets in order to verify our hypothesis that overlapping among classes is a complicating factor in highly skewed data sets. We also carried out a broadly experimental analysis with several methods (some of them proposed by us) that artificially balance skewed datasets. Our experiments show that, in general, over-sampling methods perform better than under-sampling methods. Finally, we investigated the relationship between class imbalance and small disjuncts, as well as the influence of the proportion of examples among classes in the process of labelling unlabelled cases in the semi-supervised learning algorithm Co-training. New method for combining rankings. We propose a new method called BordaRanking to construct ensembles of rankings based on borda count voting, which could be applied whenever only the rankings are available. Results show an improvement upon the base-rankings constructed by taking into account the ordering given by classifiers which output continuous-valued scores, as well as a comparable performance with the fusion of such scores.

Studies have shown that linguistic and perceptual constraints are important for speech processing. First, rule-like structures are more easily learned over vowels than over consonants. Second, sequences varying in pitch and duration are grouped following the Iambic – Trochaic Law (ITL). In this research, I investigated the origins of these linguistic and perceptual constraints. My aim was to test if vowels’ acoustic saliency was the reason why they are the preferred target for abstract computations, and to explore the extent to which the principles of the ITL come from evolutionary heritage or language experience. Results show that rats learn rules over consonants and vowels with the same ease, so saliency is insufficient to explain the asymmetries observed in humans. This also shows that animals share with humans the trochaic principle of the ITL, but they lack the iambic-grouping bias, which might rely on language experience. / Diversos estudios han encontrado que limitaciones perceptuales y de aprendizaje intervienen en el procesamiento del lenguaje. Primero, que el aprendizaje de reglas se realiza mejor sobre las vocales. Segundo, que secuencias alternando en frecuencia y duración son agrupadas siguiendo la Ley Yámbico-Trocaico (LYT). En esta investigación busqué esclarecer el origen de estas limitaciones lingüísticas y perceptuales. Mi objetivo fue estudiar si la preferencia por las vocales se debe a su prominencia acústica e investigar hasta qué punto la LYT es producto de la herencia evolutiva o de la experiencia lingüística. Los resultados muestran que las ratas computan reglas sobre vocales y consonantes, por lo que las asimetrías funcionales observadas en humanos no se explican por la saliencia acústica de las vocales. También sugieren que animales y humanos comparten el principio trocaico de la LYT, pero no el yámbico, el cual podría emerger tras años de experiencia con el lenguaje nativo.

A Study of the Effect of Cognitive Styles Learning Approaches on Identifying English Clause Tasks Lieu, Pin-huei Abstract The main purpose of this study intended to discuss the effect of Field Independent subjects(FIs), Field Dependent subjects (FDs) of junior high school using Discovery, Rule Learning approaches on identifying English clauses task. The questions explored here were: 1.How did FIs and FDs differently perform on identifying English clauses tasks. 2.How did Discovery and Rule learning approaches differently perform on identifying English clauses tasks. 3.How did FIs / FDs and Discovery/Rule learning approaches create interactive effect on identifying English clauses tasks. The study used experimental research method. The subjects were 90 third grade students of junior high school. According to the scores of Embedded Figures Test students were divided into FI and FD. Then depending on the scores of the prior test on identifying English clauses task, FIs and FDs match with two group to accept Discovery and Rule learning approaches , and each one was composed of 10 students. The instruments was ¡§ Embedded Figures Test¡¨ , ¡§self-made that clauses test ,¡¨and the information acquired was dealt with statistical testing through 2*2 ANOVA .The results indicated as followings. 1.An interactive effect of cognitive style and learning approaches were found through ANOVA. FIs using Discovery learning performed better than using Rule learning ,and FDs using Rule learning performed better using Discovery learning .In sum ,FIs appropriately use Discovery learning approach and FDs appropriately use Rule learning approach on identifying English clauses task. 2.Cognitive style lives up significantly different level .FIs performed better than those of FDs. 3.No overall difference were found between Discovery and Rule learning approach. Finally the study discussed the above results in more detail ,and provided suggestions and references of research concerning teaching of English clauses .

abstract: The goal of fact checking is to determine if a given claim holds. A promising ap- proach for this task is to exploit reference information in the form of knowledge graphs (KGs), a structured and formal representation of knowledge with semantic descriptions of entities and relations. KGs are successfully used in multiple appli- cations, but the information stored in a KG is inevitably incomplete. In order to address the incompleteness problem, this thesis proposes a new method built on top of recent results in logical rule discovery in KGs called RuDik and a probabilistic extension of answer set programs called LPMLN. This thesis presents the integration of RuDik which discovers logical rules over a given KG and LPMLN to do probabilistic inference to validate a fact. While automatically discovered rules over a KG are for human selection and revision, they can be turned into LPMLN programs with a minor modification. Leveraging the probabilistic inference in LPMLN, it is possible to (i) derive new information which is not explicitly stored in a KG with a probability associated with it, and (ii) provide supporting facts and rules for interpretable explanations for such decisions. Also, this thesis presents experiments and results to show that this approach can label claims with high precision. The evaluation of the system also sheds light on the role played by the quality of the given rules and the quality of the KG. / Dissertation/Thesis / Masters Thesis Computer Science 2018

Algoritmos de aprendizado de máquina são frequentemente os mais indicados em uma grande variedade de aplicações de mineração dados. Entretanto, a maioria das pesquisas em aprendizado de máquina refere-se ao problema bem definido de encontrar um modelo (geralmente de classificação) de um conjunto de dados pequeno, relativamente bem preparado para o aprendizado, no formato atributo-valor, no qual os atributos foram previamente selecionados para facilitar o aprendizado. Além disso, o objetivo a ser alcançado é simples e bem definido (modelos de classificação precisos, no caso de problemas de classificação). Mineração de dados propicia novas direções para pesquisas em aprendizado de máquina e impõe novas necessidades para outras. Com a mineração de dados, algoritmos de aprendizado estão quebrando as restrições descritas anteriormente. Dessa maneira, a grande contribuição da área de aprendizado de máquina para a mineração de dados é retribuída pelo efeito inovador que a mineração de dados provoca em aprendizado de máquina. Nesta tese, exploramos alguns desses problemas que surgiram (ou reaparecem) com o uso de algoritmos de aprendizado de máquina para mineração de dados. Mais especificamente, nos concentramos seguintes problemas: Novas abordagens para a geração de regras. Dentro dessa categoria, propomos dois novos métodos para o aprendizado de regras. No primeiro, propomos um novo método para gerar regras de exceção a partir de regras gerais. No segundo, propomos um algoritmo para a seleção de regras denominado Roccer. Esse algoritmo é baseado na análise ROC. Regras provêm de um grande conjunto externo de regras e o algoritmo proposto seleciona regras baseado na região convexa do gráfico ROC. Proporção de exemplos entre as classes. Investigamos vários aspectos relacionados a esse tópico. Primeiramente, realizamos uma série de experimentos em conjuntos de dados artificiais com o objetivo de testar nossa hipótese de que o grau de sobreposição entre as classes é um fator complicante em conjuntos de dados muito desbalanceados. Também executamos uma extensa análise experimental com vários métodos (alguns deles propostos neste trabalho) para balancear artificialmente conjuntos de dados desbalanceados. Finalmente, investigamos o relacionamento entre classes desbalanceadas e pequenos disjuntos, e a influência da proporção de classes no processo de rotulação de exemplos no algoritmo de aprendizado de máquina semi-supervisionado Co-training. Novo método para a combinação de rankings. Propomos um novo método, chamado BordaRank, para construir ensembles de rankings baseado no método de votação borda count. BordaRank pode ser aplicado em qualquer problema de ordenação binária no qual vários rankings estejam disponíveis. Resultados experimentais mostram uma melhora no desempenho com relação aos rankings individuais, alem de um desempenho comparável com algoritmos mais sofisticados que utilizam a predição numérica, e não rankings, para a criação de ensembles para o problema de ordenação binária. / Machine learning algorithms are often the most appropriate algorithms for a great variety of data mining applications. However, most machine learning research to date has mainly dealt with the well-circumscribed problem of finding a model (generally a classifier) given a single, small and relatively clean dataset in the attribute-value form, where the attributes have previously been chosen to facilitate learning. Furthermore, the end-goal is simple and well-defined, such as accurate classifiers in the classification problem. Data mining opens up new directions for machine learning research, and lends new urgency to others. With data mining, machine learning is now removing each one of these constraints. Therefore, machine learning's many valuable contributions to data mining are reciprocated by the latter's invigorating effect on it. In this thesis, we explore this interaction by proposing new solutions to some problems due to the application of machine learning algorithms to data mining applications. More specifically, we contribute to the following problems. New approaches to rule learning. In this category, we propose two new methods for rule learning. In the first one, we propose a new method for finding exceptions to general rules. The second one is a rule selection algorithm based on the ROC graph. Rules come from an external larger set of rules and the algorithm performs a selection step based on the current convex hull in the ROC graph. Proportion of examples among classes. We investigated several aspects related to this issue. Firstly, we carried out a series of experiments on artificial data sets in order to verify our hypothesis that overlapping among classes is a complicating factor in highly skewed data sets. We also carried out a broadly experimental analysis with several methods (some of them proposed by us) that artificially balance skewed datasets. Our experiments show that, in general, over-sampling methods perform better than under-sampling methods. Finally, we investigated the relationship between class imbalance and small disjuncts, as well as the influence of the proportion of examples among classes in the process of labelling unlabelled cases in the semi-supervised learning algorithm Co-training. New method for combining rankings. We propose a new method called BordaRanking to construct ensembles of rankings based on borda count voting, which could be applied whenever only the rankings are available. Results show an improvement upon the base-rankings constructed by taking into account the ordering given by classifiers which output continuous-valued scores, as well as a comparable performance with the fusion of such scores.

Variability in the brain’s functional network connectivity is associated with differences in cognition. The degree to which brain networks flexibly reconfigure, or alternatively remain stable, can differ across regions of cortex, across time, and across individuals. The goal of this dissertation was to investigate how the brain’s functional network architecture is reconfigured to support abstract reasoning and rule learning. I proposed that flexibility within frontoparietal cortex, combined with a stable network core, is beneficial for effective reasoning and rule learning. Experiment One investigated the activation patterns and dynamic community structure of brain networks associated with shifting task demands during abstract reasoning. Twenty-seven subjects underwent fMRI scanning during resting state and during a subsequent abstract reasoning task. When quantifying network reconfiguration between resting and task states, I found a stable system within default and somatomotor networks alongside a more flexible frontoparietal control network. The results motivated a novel understanding of how the brain performs reasoning tasks: an underlying stable functional network acts as a cognitive control mechanism, priming task-active nodes within frontoparietal cortex to variably activate for unique task conditions. Experiment Two used a dynamic network analysis to identify changes in functional brain networks that were associated with context-dependent rule learning. During fMRI scanning, twenty-nine naïve subjects were challenged to learn a set of context-dependent rules. Successful learners showed greater stability in ventral attention and somatomotor regions, increased assortative mixing of cognitive control regions as rules were learned, and greater segregation of attention networks throughout the entire task. The results suggested that a stable ventral attention network and a flexible frontoparietal control network support sustained attention and the formation of rule representations. In Experiment Three, I carried out a separate analysis of data from Experiment 2 to characterize the functional connectivity patterns with the hippocampus that emerged during successful rule learning. The results demonstrated that the hippocampal head became increasingly functionally connected to the lateral frontal pole and caudate in successful learners. Additionally, the entire hippocampus exhibited decreased functional connectivity with the mid-cingulate and precuneus in successful learners. These three experiments demonstrated that stable functional connectivity in somatomotor and ventral attention networks, combined with flexible reconfiguration of frontoparietal cortex, is advantageous for successful rule learning and abstract reasoning. Altogether, this dissertation demonstrated that individual differences in dynamic functional connectivity are associated with learning, and that stability of brain networks across time and tasks supports higher order cognition. / 2025-01-23T00:00:00Z

No description available.

Os cartões, sejam de crédito ou débito, são meios de pagamento altamente utilizados. Esse fato desperta o interesse de fraudadores. O mercado de cartões enxerga as fraudes como custos operacionais, que são repassados para os consumidores e para a sociedade em geral. Ainda, o alto volume de transações e a necessidade de combater as fraudes abrem espaço para a aplicação de técnicas de Aprendizagem de Máquina; entre elas, os classificadores. Um tipo de classificador largamente utilizado nesse domínio é o classificador baseado em regras. Entretanto, um ponto de atenção dessa categoria de classificadores é que, na prática, eles são altamente dependentes dos especialistas no domínio, ou seja, profissionais que detectam os padrões das transações fraudulentas, os transformam em regras e implementam essas regras nos sistemas de classificação. Ao reconhecer esse cenário, o objetivo desse trabalho é propor a uma arquitetura baseada em regras de associação e regressão logística - técnicas estudadas em Aprendizagem de Máquina - para minerar regras nos dados e produzir, como resultado, conjuntos de regras de detecção de transações fraudulentas e disponibilizá-los para os especialistas no domínio. Com isso, esses profissionais terão o auxílio dos computadores para descobrir e gerar as regras que embasam o classificador, diminuindo, então, a chance de haver padrões fraudulentos ainda não reconhecidos e tornando as atividades de gerar e manter as regras mais eficientes. Com a finalidade de testar a proposta, a parte experimental do trabalho contou com cerca de 7,7 milhões de transações reais de cartões fornecidas por uma empresa participante do mercado de cartões. A partir daí, dado que o classificador pode cometer erros (falso-positivo e falso-negativo), a técnica de análise sensível ao custo foi aplicada para que a maior parte desses erros tenha um menor custo. Além disso, após um longo trabalho de análise do banco de dados, 141 características foram combinadas para, com o uso do algoritmo FP-Growth, gerar 38.003 regras que, após um processo de filtragem e seleção, foram agrupadas em cinco conjuntos de regras, sendo que o maior deles tem 1.285 regras. Cada um desses cinco conjuntos foi submetido a uma modelagem de regressão logística para que suas regras fossem validadas e ponderadas por critérios estatísticos. Ao final do processo, as métricas de ajuste estatístico dos modelos revelaram conjuntos bem ajustados e os indicadores de desempenho dos classificadores também indicaram, num geral, poderes de classificação muito bons (AROC entre 0,788 e 0,820). Como conclusão, a aplicação combinada das técnicas estatísticas - análise sensível ao custo, regras de associação e regressão logística - se mostrou conceitual e teoricamente coesa e coerente. Por fim, o experimento e seus resultados demonstraram a viabilidade técnica e prática da proposta. / Credit and debit cards are two methods of payments highly utilized. This awakens the interest of fraudsters. Businesses see fraudulent transactions as operating costs, which are passed on to consumers. Thus, the high number of transactions and the necessity to combat fraud stimulate the use of machine learning algorithms; among them, rule-based classifiers. However, a weakness of these classifiers is that, in practice, they are highly dependent on professionals who detect patterns of fraudulent transactions, transform them into rules and implement these rules in the classifier. Knowing this scenario, the aim of this thesis is to propose an architecture based on association rules and logistic regression - techniques studied in Machine Learning - for mining rules on data and produce rule sets to detect fraudulent transactions and make them available to experts. As a result, these professionals will have the aid of computers to discover the rules that support the classifier, decreasing the chance of having non-discovered fraudulent patterns and increasing the efficiency of generate and maintain these rules. In order to test the proposal, the experimental part of the thesis has used almost 7.7 million transactions provided by a real company. Moreover, after a long process of analysis of the database, 141 characteristics were combined using the algorithm FP-Growth, generating 38,003 rules. After a process of filtering and selection, they were grouped into five sets of rules which the biggest one has 1,285 rules. Each of the five sets was subjected to logistic regression, so their rules have been validated and weighted by statistical criteria. At the end of the process, the goodness of fit tests were satisfied and the performance indicators have shown very good classification powers (AUC between 0.788 and 0.820). In conclusion, the combined application of statistical techniques - cost sensitive learning, association rules and logistic regression - proved being conceptually and theoretically cohesive and coherent. Finally, the experiment and its results have demonstrated the technical and practical feasibilities of the proposal.

Several real world tasks involve data that is uncertain and relational in nature. Traditional approaches like first-order logic and probabilistic models either deal with structured data or uncertainty, but not both. To address these limitations, statistical relational learning (SRL), a new area in machine learning integrating both first-order logic and probabilistic graphical models, has emerged in the recent past. The advantage of SRL models is that they can handle both uncertainty and structured/relational data. As a result, they are widely used in domains like social network analysis, biological data analysis, and natural language processing. Bayesian Logic Programs (BLPs), which integrate both first-order logic and Bayesian net- works are a powerful SRL formalism developed in the recent past. In this dissertation, we develop approaches using BLPs to solve two real world tasks – plan recognition and machine reading. Plan recognition is the task of predicting an agent’s top-level plans based on its observed actions. It is an abductive reasoning task that involves inferring cause from effect. In the first part of the dissertation, we develop an approach to abductive plan recognition using BLPs. Since BLPs employ logical deduction to construct the networks, they cannot be used effectively for abductive plan recognition as is. Therefore, we extend BLPs to use logical abduction to construct Bayesian networks and call the resulting model Bayesian Abductive Logic Programs (BALPs). In the second part of the dissertation, we apply BLPs to the task of machine reading, which involves automatic extraction of knowledge from natural language text. Most information extraction (IE) systems identify facts that are explicitly stated in text. However, much of the information conveyed in text must be inferred from what is explicitly stated since easily inferable facts are rarely mentioned. Human readers naturally use common sense knowledge and “read between the lines” to infer such implicit information from the explicitly stated facts. Since IE systems do not have access to common sense knowledge, they cannot perform deeper reasoning to infer implicitly stated facts. Here, we first develop an approach using BLPs to infer implicitly stated facts from natural language text. It involves learning uncertain common sense knowledge in the form of probabilistic first-order rules by mining a large corpus of automatically extracted facts using an existing rule learner. These rules are then used to derive additional facts from extracted information using BLP inference. We then develop an online rule learner that handles the concise, incomplete nature of natural-language text and learns first-order rules from noisy IE extractions. Finally, we develop a novel approach to calculate the weights of the rules using a curated lexical ontology like WordNet. Both tasks described above involve inference and learning from partially observed or incomplete data. In plan recognition, the underlying cause or the top-level plan that resulted in the observed actions is not known or observed. Further, only a subset of the executed actions can be observed by the plan recognition system resulting in partially observed data. Similarly, in machine reading, since some information is implicitly stated, they are rarely observed in the data. In this dissertation, we demonstrate the efficacy of BLPs for inference and learning from incomplete data. Experimental comparison on various benchmark data sets on both tasks demonstrate the superior performance of BLPs over state-of-the-art methods. / text