Sistemas de Aprendizagem Adaptativos e Inteligentes, tema de pesquisa recente no mundo, são ambientes com arquitetura e algoritmos específicos, que consideram as características individuais de cada estudante para selecionar o objeto de aprendizagem mais adequado a ser oferecido ao aluno. O rápido desenvolvimento da infraestrutura sem fio e o amplo uso de dispositivos móveis na vida diária das pessoas motivam as pesquisas relativas ao uso desses dispositivos na educação, proporcionando o m-learning. Assim, relacionado a essas linhas de pesquisa, este trabalho propõe a arquitetura AdaptMLearning, elaborada para prover a aprendizagem em plataformas móveis e não móveis, considerando a seleção de objetos de aprendizagem que melhor se adaptam a diversos aspectos, tais como: dados sobre a tecnologia utilizada para acesso; informações sobre o estilo de aprendizagem de um estudante; desempenho e tempo associados à interação do estudante com o objeto de aprendizagem; conhecimentos adquiridos pelo estudante em consonância ao conteúdo do curso; e a garantia de que não só o professor possa configurar as adaptações a serem oferecidas ao seu curso, como também o aluno tenha a possibilidade de informar sua preferência pelos tipos de mídia. Essa arquitetura é baseada no modelo de referência AHAM para sistemas adaptativos AEHS, contemplando a quádrupla: espaço do conhecimento, modelo do usuário, observações e modelo de adaptação, referente à definição lógica desses sistemas. Na AdaptMLearning, foram desenvolvidos alguns algoritmos, utilizando-se o modelo FSLSM, relacionado aos estilos de aprendizagem de um estudante e o padrão IEEE 1484 para catalogação dos objetos de aprendizagem e uso de alguns atributos de suas categorias, associados às dimensões dos estilos de aprendizagem do modelo FSLSM. O algoritmo calcula um peso para um objeto catalogado em cada dimensão e permite uma busca pelo objeto mais adequado ao estilo do estudante, além de usar a computação fuzzy, para avaliar se o estudante pode sofrer mudanças no seu estilo, deve receber reforço ou necessita de um reestudo em determinado assunto de um curso, por meio de resultados obtidos com o tempo de estudo e desempenho. Também, este trabalho apresenta o desenvolvimento e a avaliação de um simulador para a arquitetura AdaptMLearning e seus algoritmos, realizada utilizando diversos cenários de simulação, envolvendo estudantes, cursos e tecnologias com diferentes configurações. Assim sendo, com base nos resultados obtidos por meio da avaliação, foi possível discutir, analisar e identificar o potencial de uso da AdaptMLearning e de seus algoritmos em uma situação real para elaboração de um ambiente de aprendizagem ou agregação a um ambiente existente. / Intelligent and Adaptive Learning Systems, subject of recent research in the world, are environments with specific architectures and algorithms, designed considering the individual characteristics of each student. The rapid development of wireless infrastructures and wide use of mobile devices in people\'s everyday life encourage research about the use of these devices in education, providing the mlearning. In the context of such research, this work proposes the AdaptMLearning architecture that was designed to be a learning infrastructure for mobile and nonmobile platforms. This architecture provides a selection of learning objects that takes into account as adaptation criteria the following data: the mobile device\'s technological specification; the student\'s learning style information, his/her performance and spent time associated to the student\'s interaction with the learning object; previously acquired knowledge by the student related to the course\'s content. In addition, it also allows the teacher to interfere in the adaptation criteria used during the study simulation, and allows the student to indicate his/her preferences for media types. This architecture is based on AHAM reference model for adaptive systems AEHS and uses the quadruple: the knowledge space, the user model, the observations and the model adaptation, referring to the logical definition of these systems. To implement the AdaptMLearning architecture some algorithms using the FSLSM model related to the student\'s learning styles were developed. The algorithms use the IEEE 1484 for cataloging learning objects and some of its categories and attributes associated with dimensions of learning styles FSLSM model, are used to compute a weight of an object in each dimension allowing a search of the most appropriate object according to the student\'s learning styles; and the use of fuzzy computing, considering that the student\'s learning style can change, determines if the student has to receive reinforcement or need a new study in a particular subject of a course, when the student gets unsatisfactory results in terms of timing and performance in a course\'s subject. Also, this work also presents the development and evaluation of a simulator for the AdaptMLearning architecture and their algorithms. The evaluation of the simulator was done by means of many simulations scenarios, considering students, courses and technologies with different settings. Based on the results obtained from the evaluation it was possible to discuss, analyze and identify the potential use of AdaptMLearning architecture and their algorithms in a real situation for developing a learning environment or its aggregation to an existing environment.

Em Aprendizado de Máquina - AM não existe um único algoritmo que é sempre melhor para todos os domínios de aplicação. Na prática, diversas pesquisas mostram que Redes Neurais Artificiais - RNAs têm um 'bias' indutivo apropriado para diversos domínios. Em razão disso, RNAs têm sido aplicadas na resolução de vários problemas com desempenho satisfatório. Sistemas de AM simbólico possuem um 'bias' indutivo menos flexível do que as RNAs. Enquanto que as RNAs são capazes de aprender qualquer função, sistemas de AM simbólico geralmente aprendem conceitos que podem ser descritos na forma de hiperplanos. Por outro lado, sistemas de AM simbólico representam o conceito induzido por meio de estruturas simbólicas, as quais são geralmente compreensíveis pelos seres humanos. Assim, sistemas de AM simbólico são preferíveis quando é essencial a compreensibilidade do conceito induzido. RNAs carecem da capacidade de explicar suas decisões, uma vez que o conhecimento é codificado na forma de valores de seus pesos e 'thresholds'. Essa codificação é difícil de ser interpretada por seres humanos. Em diversos domínios de aplicação, tal como aprovação de crédito e diagnóstico médico, prover uma explicação sobre a classificação dada a um determinado caso é de crucial importância. De um modo similar, diversos usuários de sistemas de AM simbólico desejam validar o conhecimento induzido, com o objetivo de assegurar que a generalização feita pelo algoritmo é correta. Para que RNAs sejam aplicadas em um maior número de domínios, diversos pesquisadores têm proposto métodos para extrair conhecimento compreensível de RNAs. As principais contribuições desta tese são dois métodos que extraem conhecimento simbólico de RNAs. Os métodos propostos possuem diversas vantagens sobre outros métodos propostos previamente, tal como ser aplicáveis a qualquer arquitetura ou algoritmo de aprendizado de RNAs supervisionadas. O primeiro método proposto utiliza sistemas de AM simbólico para extrair conhecimento de RNAs, e o segundo método proposto estende o primeiro, combinado o conhecimento induzido por diversos sistemas de AM simbólico por meio de um Algoritmo Genético - AG. Os métodos propostos são analisados experimentalmente em diversos domínios de aplicação. Ambos os métodos são capazes de extrair conhecimento simbólico com alta fidelidade em relação à RNA treinada. Os métodos propostos são comparados com o método TREPAN, apresentando resultados promissores. TREPAN é um método bastante conhecido para extrair conhecimento de RNAs. / In Machine Learning - ML there is not a single algorithm that is the best for all application domains. In practice, several research works have shown that Artificial Neural Networks - ANNs have an appropriate inductive bias for several domains. Thus, ANNs have been applied to a number of data sets with high predictive accuracy. Symbolic ML algorithms have a less flexible inductive bias than ANNs. While ANNs can learn any input-output mapping, i.e., ANNs have the universal approximation property, symbolic ML algorithms frequently learn concepts describing them using hyperplanes. On the other hand, symbolic algorithms are needed when a good understating of the decision process is essential, since symbolic ML algorithms express the knowledge induced using symbolic structures that can be interpreted and understood by humans. ANNs lack the capability of explaining their decisions since the knowledge is encoded as real-valued weights and biases of the network. This encoding is difficult to be interpreted by humans. In several application domains, such as credit approval and medical diagnosis, providing an explanation related to the classification given to a certain case is of crucial importance. In a similar way, several users of ML algorithms desire to validate the knowledge induced, in order to assure that the generalization made by the algorithm is correct. In order to apply ANNs to a larger number of application domains, several researches have proposed methods to extract comprehensible knowledge from ANNs. The primary contribution of this thesis consists of two methods that extract symbolic knowledge, expressed as decision rules, from ANNs. The proposed methods have several advantages over previous methods, such as being applicable to any architecture and supervised learning algorithm of ANNs. The first method uses standard symbolic ML algorithm to extract knowledge from ANNs, and the second method extends the first method by combining the knowledge induced by several symbolic ML algorithms through the application of a Genetic Algorithm - GA. The proposed methods are experimentally analyzed in a number of application domains. Results show that both methods are capable to extract symbolic knowledge having high fidelity with trained ANNs. The proposed methods are compared with TREPAN, showing promising results. TREPAN is a well known method to extract knowledge from ANNs.

Sistemas de Aprendizagem Adaptativos e Inteligentes, tema de pesquisa recente no mundo, são ambientes com arquitetura e algoritmos específicos, que consideram as características individuais de cada estudante para selecionar o objeto de aprendizagem mais adequado a ser oferecido ao aluno. O rápido desenvolvimento da infraestrutura sem fio e o amplo uso de dispositivos móveis na vida diária das pessoas motivam as pesquisas relativas ao uso desses dispositivos na educação, proporcionando o m-learning. Assim, relacionado a essas linhas de pesquisa, este trabalho propõe a arquitetura AdaptMLearning, elaborada para prover a aprendizagem em plataformas móveis e não móveis, considerando a seleção de objetos de aprendizagem que melhor se adaptam a diversos aspectos, tais como: dados sobre a tecnologia utilizada para acesso; informações sobre o estilo de aprendizagem de um estudante; desempenho e tempo associados à interação do estudante com o objeto de aprendizagem; conhecimentos adquiridos pelo estudante em consonância ao conteúdo do curso; e a garantia de que não só o professor possa configurar as adaptações a serem oferecidas ao seu curso, como também o aluno tenha a possibilidade de informar sua preferência pelos tipos de mídia. Essa arquitetura é baseada no modelo de referência AHAM para sistemas adaptativos AEHS, contemplando a quádrupla: espaço do conhecimento, modelo do usuário, observações e modelo de adaptação, referente à definição lógica desses sistemas. Na AdaptMLearning, foram desenvolvidos alguns algoritmos, utilizando-se o modelo FSLSM, relacionado aos estilos de aprendizagem de um estudante e o padrão IEEE 1484 para catalogação dos objetos de aprendizagem e uso de alguns atributos de suas categorias, associados às dimensões dos estilos de aprendizagem do modelo FSLSM. O algoritmo calcula um peso para um objeto catalogado em cada dimensão e permite uma busca pelo objeto mais adequado ao estilo do estudante, além de usar a computação fuzzy, para avaliar se o estudante pode sofrer mudanças no seu estilo, deve receber reforço ou necessita de um reestudo em determinado assunto de um curso, por meio de resultados obtidos com o tempo de estudo e desempenho. Também, este trabalho apresenta o desenvolvimento e a avaliação de um simulador para a arquitetura AdaptMLearning e seus algoritmos, realizada utilizando diversos cenários de simulação, envolvendo estudantes, cursos e tecnologias com diferentes configurações. Assim sendo, com base nos resultados obtidos por meio da avaliação, foi possível discutir, analisar e identificar o potencial de uso da AdaptMLearning e de seus algoritmos em uma situação real para elaboração de um ambiente de aprendizagem ou agregação a um ambiente existente. / Intelligent and Adaptive Learning Systems, subject of recent research in the world, are environments with specific architectures and algorithms, designed considering the individual characteristics of each student. The rapid development of wireless infrastructures and wide use of mobile devices in people\'s everyday life encourage research about the use of these devices in education, providing the mlearning. In the context of such research, this work proposes the AdaptMLearning architecture that was designed to be a learning infrastructure for mobile and nonmobile platforms. This architecture provides a selection of learning objects that takes into account as adaptation criteria the following data: the mobile device\'s technological specification; the student\'s learning style information, his/her performance and spent time associated to the student\'s interaction with the learning object; previously acquired knowledge by the student related to the course\'s content. In addition, it also allows the teacher to interfere in the adaptation criteria used during the study simulation, and allows the student to indicate his/her preferences for media types. This architecture is based on AHAM reference model for adaptive systems AEHS and uses the quadruple: the knowledge space, the user model, the observations and the model adaptation, referring to the logical definition of these systems. To implement the AdaptMLearning architecture some algorithms using the FSLSM model related to the student\'s learning styles were developed. The algorithms use the IEEE 1484 for cataloging learning objects and some of its categories and attributes associated with dimensions of learning styles FSLSM model, are used to compute a weight of an object in each dimension allowing a search of the most appropriate object according to the student\'s learning styles; and the use of fuzzy computing, considering that the student\'s learning style can change, determines if the student has to receive reinforcement or need a new study in a particular subject of a course, when the student gets unsatisfactory results in terms of timing and performance in a course\'s subject. Also, this work also presents the development and evaluation of a simulator for the AdaptMLearning architecture and their algorithms. The evaluation of the simulator was done by means of many simulations scenarios, considering students, courses and technologies with different settings. Based on the results obtained from the evaluation it was possible to discuss, analyze and identify the potential use of AdaptMLearning architecture and their algorithms in a real situation for developing a learning environment or its aggregation to an existing environment.

Σκοπός της διατριβής είναι η ανάλυση, η μελέτη και η μοντελοποίηση της συμπεριφοράς τόσο των ευφυών πρακτόρων όσο και των χρηστών σε εικονικά περιβάλλοντα μάθησης, με τη χρήση τεχνικών υπολογιστικής νοημοσύνης. Το θεματικό αντικείμενο της διδακτορικής διατριβής αποτελεί ένα σύγχρονο αντικείμενο βασικής έρευνας με μεγάλο εύρος πρακτικών εφαρμογών. Η βάση της ερευνητικής δραστηριότητας εστιάζεται σε δύο βασικούς τομείς: 1. Προσαρμόσιμη μοντελοποίηση συμπεριφορών ευφυών πρακτόρων σε εικονικά περιβάλλοντα μάθησης, σύμφωνα με κανόνες βελτιστοποίησης της μαθησιακής επίδρασης στο χρήστη μέσα στο εικονικό περιβάλλον μάθησης. 2. Μοντελοποίηση χρηστών εικονικών περιβαλλόντων μάθησης, με στόχο τη βελτιστοποίηση της μαθησιακής επίδρασης στο χρήστη. Για τη μοντελοποίηση, τόσο της συμπεριφοράς των ευφυών πρακτόρων, όσο και των χρηστών, χρησιμοποιήθηκαν προηγμένες τεχνικές υπολογιστικής νοημοσύνης (Bayesian Δίκτυα, Γενετικοί και Εξελικτικοί Αλγόριθμοι). Αυτές οι τεχνικές, εκτός από την ευφυΐα, ενσωματώνουν και το επιθυμητό χαρακτηριστικό της προσαρμοσιμότητας, με την έννοια ότι μπορούν να προσαρμόζονται στις αλλαγές του περιβάλλοντος. Τα παραπάνω αποτελέσματα αξιολογήθηκαν στη χρήση τους σε Ευφυή Εικονικά Συστήματα Μάθησης βασισμένα στο Web (Intelligent Virtual Learning Systems – IVLS), τα οποία αποτελούν ουσιαστικά το μέσον εξαγωγής συμπερασμάτων και υποστηρικτικού υλικού για τη μετρήσιμη συμπεριφορά τόσο των ευφυών πρακτόρων όσο και των χρηστών, μέσα σε τέτοια περιβάλλοντα. / The main objectives of the thesis are the analysis, study and the provision of a behavior modeling procedure of the intelligent agents and the students in virtual e-learning systems using computational intelligence techniques. The domain of the thesis is a topic of basic research with a large scale of applied results. The basis of the research is focused in two main sectors: 1. Adaptive behavior modeling of intelligent agents in virtual learning systems, according to specific optimization rules of the learning process during the interaction of the user/student with the e-learning environment. 2. User modeling of the users of virtual learning environments towards the optimization of the learning process. For the modeling procedure of the behavior of intelligent agents and of the users specific computational intelligence techniques have been applied (Bayesian Networks, Genetic και Evolutionary Algorithms). The specific techniques provide intelligence to the system and the most important the feature of adaptability. The aforementioned results have been evaluated on Intelligent Virtual Learning Systems, which constitute the medium for the inference of the results and the mean for supportive material for the measurable behavior of the intelligent agents and of the users in Intelligent Virtual Learning Systems.

Thesis (Ph. D.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Bioengineering, Biomedical Engineering, 2009. / Includes bibliographical references.

La plupart des systèmes d'apprentissage interactifs actuels s'appuient sur des protocoles prédéfinis qui peuvent être contraignants pour l'utilisateur. Cette thèse aborde le problème de l'interprétation des instructions, afin de relâcher la contrainte de prédéterminer leurs significations. Nous proposons un système permettant à un humain de guider l'apprentissage d'un robot, à travers des instructions non labellisées. Notre approche consiste à ancrer la signification des signaux instructifs dans le processus d'apprentissage de la tâche et à les utiliser simultanément pour guider l'apprentissage. Cette approche offre plus de liberté à l'humain dans le choix des signaux qu'il peut utiliser, et permet de réduire les efforts d'ingénierie en supprimant la nécessité d'encoder la signification de chaque signal instructif.Nous implémentons notre système sous la forme d'une architecture modulaire, appelée TICS, qui permet de combiner différentes sources d'information: une fonction de récompense, du feedback évaluatif et des instructions non labellisées. Cela offre une plus grande souplesse dans l'apprentissage, en permettant à l'utilisateur de choisir entre différents modes d'apprentissage. Nous proposons plusieurs méthodes pour interpréter les instructions, et une nouvelle méthode pour combiner les feedbacks évaluatifs avec une fonction de récompense prédéfinie.Nous évaluons notre système à travers une série d'expériences, réalisées à la fois en simulation et avec de vrais robots. Les résultats expérimentaux démontrent l'efficacité de notre système pour accélérer le processus d'apprentissage et pour réduire le nombre d'interactions avec l'utilisateur. / Most of current interactive learning systems rely on predefined protocols that constrain the interaction with the user. Relaxing the constraints of interaction protocols can therefore improve the usability of these systems.This thesis tackles the question of interpreting human instructions, in order to relax the constraints about predetermining their meanings. We propose a framework that enables a human teacher to shape a robot behaviour, by interactively providing it with unlabeled instructions. Our approach consists in grounding the meaning of instruction signals in the task learning process, and using them simultaneously for guiding the latter. This approach has a two-fold advantage. First, it provides more freedom to the teacher in choosing his preferred signals. Second, it reduces the required engineering efforts, by removing the necessity to encode the meaning of each instruction signal. We implement our framework as a modular architecture, named TICS, that offers the possibility to combine different information sources: a predefined reward function, evaluative feedback and unlabeled instructions. This allows for more flexibility in the teaching process, by enabling the teacher to switch between different learning modes. Particularly, we propose several methods for interpreting instructions, and a new method for combining evaluative feedback with a predefined reward function. We evaluate our framework through a series of experiments, performed both in simulation and with real robots. The experimental results demonstrate the effectiveness of our framework in accelerating the task learning process, and in reducing the number of required interactions with the teacher.

Made available in DSpace on 2016-08-17T14:52:56Z (GMT). No. of bitstreams: 1 Cicero Costa Quarto.pdf: 2285670 bytes, checksum: 94c0ecee3b4b6e4b82daa5b758aa57b2 (MD5) Previous issue date: 2006-05-25 / Nowadays, socio-affective factors, as cooperation, motivation, socio-cognitive affinity, proactivity, interaction and others, have been well explored in collaborative learning environments. The reason for that is because these factors would play an important role in group collaboration, as well as they would act in the construction of the human being relationships in a socio-cultural perspective. According to the vision of some educational researchers, psico-pedagogues and psychologists, in collaborative learning activities, socio-affective individual abilities should be conjugated in order to produce a collective and effective work in the construction of knowledge. Although some pedagogues and other educational researchers point out the importance of considering those factors in collaborative learning activities, few works are appreciating them. This way, the proposal of this work is to define some socio-affective factors to be inferred in collaborative learning systems in order to promote collaboration in these environments. The work will also show the importance of these socio-factors for those virtual environments. It will be also presented mechanisms for the inference of the considered socio-affective factors. / Atualmente, fatores sócio-afetivos, como cooperação, motivação, afinidades sócio-cognitivas, proatividade, interação, entre outros, tendem ser bastante explorados na relação professor-aprendiz e entre aprendizes, de forma que os resultados da construção do conhecimento sejam alcançados de forma colaborativa. A razão disto é que estes fatores desempenhariam um papel de fomento à colaboração, bem como atuariam na construção das relações do ser humano dentro de uma perspectiva sócio-cultural. Segundo a visão de alguns pesquisadores da educação, psicopedagogos e de psicólogos, em atividades colaborativas de aprendizagem, habilidades individuais sócio-afetivas de um indivíduo precisam ser conjugadas com as de outras pessoas de forma a produzirem um trabalho coletivo. Embora os padagogos e outros pesquisadores da educação apontem a importância de considerar esses fatores em atividades colaborativas de aprendizagem, poucos ambientes educacionais colaborativos assim estão fazendo. Desta maneira, a proposta deste trabalho é definir fatores sócio-afetivos a serem considerados em ambientes colaborativos de aprendizagem a fim de promover a colaboração nestes ambientes. O trabalho também mostrará a importância dos fatores sócio-afetivos para àqueles ambientes virtuais. Serão, também, propostos mecanismos para a inferência dos fatores sócio-afetivos considerados.

Notre étude relève du domaine de la didactique des langues et plus particulièrement sur la focalisation sur l’utilisation des présentations PowerPoint pour les réalisations des tâches. Ces dernières jouent un rôle important dans le déclenchement de processus d’apprentissage. Lorsque les apprenants réalisent des tâches sur support PowerPoint,interagissent ensemble pour construire du sens, ils sont dotés d’un statut d’acteurs sociaux.Cette étude se donne alors comme objectif d’améliorer la pratique des apprenants en classe et de résoudre certaines de leurs difficultés didactiques et pédagogiques à travers un dispositif hybride. Celui-ci est fondé sur des macro-tâches réalisées majoritairement en semi distance et mise en place majoritairement en présentiel à travers des exposés techniques. Ces derniers ont été conçus pour encourager le développement de performances langagières attendues en production orale des apprenants.Elle se base sur une recherche-action qui a été menée en Ouganda pour des apprenants anglophones qui apprennent le français comme langue étrangère à Makerere UniversityBusiness School (MUBS) à Kampala. Cette étude a porté sur un exposé technique oral parles apprenants du Français sur Objectif Spécifique (FOS) à (MUBS) en Ouganda.Cette recherche-action vise à améliorer l’expression orale en FOS des apprenants de l’université MUBS. Nous avons donc menée des multiples expérimentations qui nous ont permises dans un premier temps de questionner l’impact d’un exposé oral des tâches réelles collectivement élaborée et présentée sur support Power Point sur la production orale de ces apprenants. Ces tâches avaient comme objectif d’encourager les apprenants de transformer un texte en titre, sous-titres et paragraphes, puis de présenter leur travail sous forme de diaporama avec PowerPoint. Le but était d’éviter la lecture linéaire de l’exposé,afin d’accroître leur confiance en eux-mêmes et dans l’interaction en FOS. Grâce à la recherche-action, nous avons pu définir précisément en quoi et pourquoi les choix de nos tâches, de nos activités devraient avoir un effet positif sur notre public cible. / The initial objective of this study, which lies within the field of language teaching andespecially on the role of information and Communication Technology (ICT), is to investigate the potential of ICT in triggering oral language development in the learners of French for Specific purposes (FSP) at Makerere University Business School. This studyadopts action research that focuses on the role of technologies deployed in oral technical presentations of macro-tasks such as the use of MS Office. The aim is to enhance Frenchlearners’ skills in French for Specific purposes. The social constructivist or cultural hypotheses posit that social interaction plays an important role in L2 acquisition (French in this case) in FSP classes through a hybrid environment based on macro-tasks performed indistance and presented in class.The current action research project involved identifying and putting into place a learningsystem for learners of FSP who experienced several difficulties with their spoken French inthe learning process. It further posits that learners construct the new language through socially mediated interaction. Subsequently, this involved establishing whether the use ofPowerPoint presentation (PPP) would engage learners of FSP in collective actions both inthe classroom and in the real world activities. In addition, there was an attempt to establishif relevant web quest materials were likely to enhance oral language acquisition and prompt learners to take responsibility for their own learning.

Em Aprendizado de Máquina - AM não existe um único algoritmo que é sempre melhor para todos os domínios de aplicação. Na prática, diversas pesquisas mostram que Redes Neurais Artificiais - RNAs têm um 'bias' indutivo apropriado para diversos domínios. Em razão disso, RNAs têm sido aplicadas na resolução de vários problemas com desempenho satisfatório. Sistemas de AM simbólico possuem um 'bias' indutivo menos flexível do que as RNAs. Enquanto que as RNAs são capazes de aprender qualquer função, sistemas de AM simbólico geralmente aprendem conceitos que podem ser descritos na forma de hiperplanos. Por outro lado, sistemas de AM simbólico representam o conceito induzido por meio de estruturas simbólicas, as quais são geralmente compreensíveis pelos seres humanos. Assim, sistemas de AM simbólico são preferíveis quando é essencial a compreensibilidade do conceito induzido. RNAs carecem da capacidade de explicar suas decisões, uma vez que o conhecimento é codificado na forma de valores de seus pesos e 'thresholds'. Essa codificação é difícil de ser interpretada por seres humanos. Em diversos domínios de aplicação, tal como aprovação de crédito e diagnóstico médico, prover uma explicação sobre a classificação dada a um determinado caso é de crucial importância. De um modo similar, diversos usuários de sistemas de AM simbólico desejam validar o conhecimento induzido, com o objetivo de assegurar que a generalização feita pelo algoritmo é correta. Para que RNAs sejam aplicadas em um maior número de domínios, diversos pesquisadores têm proposto métodos para extrair conhecimento compreensível de RNAs. As principais contribuições desta tese são dois métodos que extraem conhecimento simbólico de RNAs. Os métodos propostos possuem diversas vantagens sobre outros métodos propostos previamente, tal como ser aplicáveis a qualquer arquitetura ou algoritmo de aprendizado de RNAs supervisionadas. O primeiro método proposto utiliza sistemas de AM simbólico para extrair conhecimento de RNAs, e o segundo método proposto estende o primeiro, combinado o conhecimento induzido por diversos sistemas de AM simbólico por meio de um Algoritmo Genético - AG. Os métodos propostos são analisados experimentalmente em diversos domínios de aplicação. Ambos os métodos são capazes de extrair conhecimento simbólico com alta fidelidade em relação à RNA treinada. Os métodos propostos são comparados com o método TREPAN, apresentando resultados promissores. TREPAN é um método bastante conhecido para extrair conhecimento de RNAs. / In Machine Learning - ML there is not a single algorithm that is the best for all application domains. In practice, several research works have shown that Artificial Neural Networks - ANNs have an appropriate inductive bias for several domains. Thus, ANNs have been applied to a number of data sets with high predictive accuracy. Symbolic ML algorithms have a less flexible inductive bias than ANNs. While ANNs can learn any input-output mapping, i.e., ANNs have the universal approximation property, symbolic ML algorithms frequently learn concepts describing them using hyperplanes. On the other hand, symbolic algorithms are needed when a good understating of the decision process is essential, since symbolic ML algorithms express the knowledge induced using symbolic structures that can be interpreted and understood by humans. ANNs lack the capability of explaining their decisions since the knowledge is encoded as real-valued weights and biases of the network. This encoding is difficult to be interpreted by humans. In several application domains, such as credit approval and medical diagnosis, providing an explanation related to the classification given to a certain case is of crucial importance. In a similar way, several users of ML algorithms desire to validate the knowledge induced, in order to assure that the generalization made by the algorithm is correct. In order to apply ANNs to a larger number of application domains, several researches have proposed methods to extract comprehensible knowledge from ANNs. The primary contribution of this thesis consists of two methods that extract symbolic knowledge, expressed as decision rules, from ANNs. The proposed methods have several advantages over previous methods, such as being applicable to any architecture and supervised learning algorithm of ANNs. The first method uses standard symbolic ML algorithm to extract knowledge from ANNs, and the second method extends the first method by combining the knowledge induced by several symbolic ML algorithms through the application of a Genetic Algorithm - GA. The proposed methods are experimentally analyzed in a number of application domains. Results show that both methods are capable to extract symbolic knowledge having high fidelity with trained ANNs. The proposed methods are compared with TREPAN, showing promising results. TREPAN is a well known method to extract knowledge from ANNs.

Research demonstrates those who fail to learn to read well face unfair and lifelong societal disadvantage (Allington, 2011; Castles et al., 2018; Frontier, College, 2018). The number of children who fail to learn to read proficiently remains unacceptable and persists even as research suggests practices to help struggling readers (Allington, 2011; Castles et al., 2018). Building upon dismal findings from literacy networks and evidence from empirical research this study addresses this problem by exploring how contextual factors influence teachers’ learning and practice and student early reading achievement through two research questions: 1) How do contextual variables at the school, board and provincial level influence the planning, delivery and uptake of early reading professional learning opportunities? 2) How do teachers perceive the relationships between (a) their professional learning experiences, (b) their classroom early reading practices, and (c) student reading outcomes? This complexivist multiple instrumental case study explores the role of context upon teachers’ (N = 6) perspectives in three diverse schools (rural, urban and suburban) in one school board with the voices of principals (N = 3) and board-level reading experts (N = 3) providing additional layers of context. Within-case findings demonstrate the importance of meeting local teacher and student needs. Contextual networks represent pathways leading to learning, teaching and student reading development. Cross-case findings reveal the universal needs of the participants for meeting students’ core social and academic needs. Finally, a conceptual framework depicts the interaction of contextual factors within the teaching, learning and student achievement process. Theoretical, empirical and practical implications anchor a discussion proposing a research agenda situating teacher early reading learning into a professional learning collective compassionate to the learning needs of teachers who in turn can be more responsive to the local and universal needs of their students.