Este trabalho investiga Aprendizado Indutivo de Máquina como função das linguagens de descrição, utilizadas para expressar instancias, conceitos e teoria do domínio. A ampliação do poder de representação do aprendizado proporcional e abordada no contexto de indução construtiva, no domínio de funções booleanas, com a proposta de uma estratégia de composição de atributos denominada root-fringe. Avaliações experimentais dessa e de outras estratégias de construção de novos atributos foram conduzidas e os resultados analisados. Dois métodos de poda, para tratamento de ruídos, em aprendizado de arvores de decisão, foram avaliados num ambiente de indução construtiva e os resultados discutidos. Devido a limitação do aprendizado proposicional, foram investigadas formas de ampliação dos limites do aprendizado, através da ampliação do poder representacional das linguagens de descrição. Foi escolhida Programação Lógica Indutiva - PLI - que e um paradigma de aprendizado indutivo que usa restrições de Lógica de Primeira Ordem como linguagens de descrição. O aprendizado em PLI só é factível quando as linguagens utilizadas estão restritas e é fortemente controlado, caso contrário, o aprendizado em PLI se torna indecidível. A pesquisa em PLI se direcionou a formas de restrição das linguagens de descrição da teoria do domínio e de hipóteses. Três algoritmos que \"traduzem\" a teoria do domínio de sua forma intencional, para extensional, são apresentados. As implementações de dois deles são discutidas. As implementações realizadas deram origem a dois ambientes experimentais de aprendizado: o ambiente proposicional experimental, do qual fazem parte o ambiente experimental construtivo, e o ambiente experimental relacional. / This work investigates Inductive Machine Learning as a function of the description languages employed to express instances, concepts and domain theory. The enlargement of the representational power of propositional learning methods is approached via constructive induction, in the domain of boolean functions, through the proposal of a bias for composing attributes, namely, the bias root-fringe. Experimental evaluation of root-fringe, as well as other biases for constructing new attributes was conducted and the results analyzed. Two pruning methods for decision trees were evaluated in an environment of constructive induction and the results discussed. Due to the limitations of propositional learning, ways of enlarging the limits of the learning process were investigated through enlarging the representational power of the description languages. It was chosen Inductive Logic Programming - ILP - that is an inductive learning paradigm that uses restrictions of First Order Logic as description languages. Learning using ILP is only feasible when the languages are restricted and are strongly controlled; otherwise, learning in ILP becomes undecidible. Research work in ILP was directed towards restricting domain theory and hypotheses description languages. Three algorithms that \"translate\" the intentional expression of a domain theory into its extensional expression are presented. The implementations of two of them are discussed. The implementations gave rise to two experimental learning environments: the propositional environment, which includes the constructive environment, and the relational environment.

In order to develop quality and excellence in e-Learning environment, manyinitiatives have been carried out in developing countries. In Bangladesh Informationand communication technologies (ICTS) are considered valuable tools for educationbut there is no proper framework for the country to develop a quality e-Learningsystem. Though it is somewhat used in higher level of studies but it is still new inprimary education system. If primary education system can be developed through elearning,then it will be more beneficial for higher level of studies.Our goal is to introduce a possible framework to adopt a quality e-Learning system inprimary educational institutes. So that the primary level education system can bedeveloped and take the advantages of e-Learning system.The result of this study would create an impact for the community who are stillindifferent about the development of primary education system and prompt thedecision makers of the primary educational institute to introduce e-Learning system intheir institutes through quality framework for e-learning. / Program: Magisterutbildning i informatik

O presente trabalho propõe um novo modelo de rede neural artificial voltado a aplicações robóticas, em especial a tarefas de natureza espaço-temporal e de horizonte infinito. Este modelo apresenta três características que o tornam único e que foram tomadas como guia para a sua concepção: auto-organização, representação temporal e aprendizado construtivo. O algoritmo de aprendizagem auto-organizada incorpora todos os mecanismos que são básicos para a auto-organização: competição global, cooperação local e auto-amplificação seletiva. A rede neural é suprida com propriedades dinâmicas através de uma memória de curto prazo. A memória de curto prazo é inserida na estrutura da rede por meio de integradores e diferenciadores, os quais são implementados na camada de entrada da rede. Nesta abordagem existe uma evidente separação de papéis: a rede é responsável pela não-linearidade e a memória é responsável pelo tempo. A construção automática da arquitetura da rede neural é realizada de acordo com uma unidade de habituação. A unidade de habituação regula o crescimento e a poda de neurônios. O procedimento de inclusão, adaptação e remoção de conexões sinápticas é realizado conforme o método de aprendizado hebbiano competitivo. Em muitos problemas práticos, como os existentes na área da robótica, a auto-organização, a representação temporal e o aprendizado construtivo são fatores imprescindíveis para o sucesso da tarefa. A grande dificuldade e, ao mesmo tempo, a principal contribuição deste trabalho consiste em integrar tais tecnologias em uma arquitetura de rede neural artificial de maneira eficiente. Estudos de caso foram elaborados para validar e, principalmente, determinar as potencialidades e as limitações do modelo neural proposto. Os cenários abrangeram tarefas simples de classificação de padrões e segmentação temporal. Os resultados preliminares obtidos demonstraram a eficiência do modelo neural proposto frente às arquiteturas conexionistas existentes e foram considerados bastante satisfatórios com relação aos parâmetros avaliados. No texto são apresentados, também, alguns aspectos teóricos das ciências cognitivas, os fundamentos de redes neurais artificiais, o detalhamento de uma ferramenta de simulação robótica, conclusões, limitações e possíveis trabalhos futuros. / The present work proposes a new artificial neural network model suitable for robotic applications, in special to spatiotemporal tasks and infinite horizon tasks. This model has three characteristics which make it unique and are taken as means to guide its conception: self-organization, temporal representation and constructive learning. The algorithm of self-organizing learning incorporates all the mechanisms that are basic to the self-organization: global competition, local cooperation and selective self-amplification. The neural network is supplied with dynamic properties through a short-term memory. The short-term memory is added in the network structure by means of integrators and differentiators, which are implemented in the input layer of the network. In this approach exists an evident separation of roles: the network is responsible for the non-linearity and the memory is responsible for the time. The automatic construction of the neural network architecture is carried out taking into account habituation units. The habituation unit regulates the growing and the pruning of neurons. The procedure of inclusion, adaptation and removal of synaptic connections is carried out in accordance with competitive hebbian learning technique. In many practical problems, as the ones in the robotic area, self-organization, temporal representation and constructive learning are essential factors to the success of the task. The great difficulty and, at the same time, the main contribution of this work consists in the integration of these technologies in a neural network architecture in an efficient way. Some case studies have been elaborated to validate and, mainly, to determine the potentialities and the limitations of the proposed neural model. The experiments comprised simple tasks of pattern classification and temporal segmentation. Preliminary results have shown the good efficiency of the neural model compared to existing connectionist architectures and they have been considered sufficiently satisfactory with regard to the evaluated parameters. This text also presents some theoretical aspects of the cognitive science area, the fundamentals of artificial neural networks, the details of a robotic simulation tool, the conclusions, limitations and possible future works.

O presente trabalho propõe um novo modelo de rede neural artificial voltado a aplicações robóticas, em especial a tarefas de natureza espaço-temporal e de horizonte infinito. Este modelo apresenta três características que o tornam único e que foram tomadas como guia para a sua concepção: auto-organização, representação temporal e aprendizado construtivo. O algoritmo de aprendizagem auto-organizada incorpora todos os mecanismos que são básicos para a auto-organização: competição global, cooperação local e auto-amplificação seletiva. A rede neural é suprida com propriedades dinâmicas através de uma memória de curto prazo. A memória de curto prazo é inserida na estrutura da rede por meio de integradores e diferenciadores, os quais são implementados na camada de entrada da rede. Nesta abordagem existe uma evidente separação de papéis: a rede é responsável pela não-linearidade e a memória é responsável pelo tempo. A construção automática da arquitetura da rede neural é realizada de acordo com uma unidade de habituação. A unidade de habituação regula o crescimento e a poda de neurônios. O procedimento de inclusão, adaptação e remoção de conexões sinápticas é realizado conforme o método de aprendizado hebbiano competitivo. Em muitos problemas práticos, como os existentes na área da robótica, a auto-organização, a representação temporal e o aprendizado construtivo são fatores imprescindíveis para o sucesso da tarefa. A grande dificuldade e, ao mesmo tempo, a principal contribuição deste trabalho consiste em integrar tais tecnologias em uma arquitetura de rede neural artificial de maneira eficiente. Estudos de caso foram elaborados para validar e, principalmente, determinar as potencialidades e as limitações do modelo neural proposto. Os cenários abrangeram tarefas simples de classificação de padrões e segmentação temporal. Os resultados preliminares obtidos demonstraram a eficiência do modelo neural proposto frente às arquiteturas conexionistas existentes e foram considerados bastante satisfatórios com relação aos parâmetros avaliados. No texto são apresentados, também, alguns aspectos teóricos das ciências cognitivas, os fundamentos de redes neurais artificiais, o detalhamento de uma ferramenta de simulação robótica, conclusões, limitações e possíveis trabalhos futuros. / The present work proposes a new artificial neural network model suitable for robotic applications, in special to spatiotemporal tasks and infinite horizon tasks. This model has three characteristics which make it unique and are taken as means to guide its conception: self-organization, temporal representation and constructive learning. The algorithm of self-organizing learning incorporates all the mechanisms that are basic to the self-organization: global competition, local cooperation and selective self-amplification. The neural network is supplied with dynamic properties through a short-term memory. The short-term memory is added in the network structure by means of integrators and differentiators, which are implemented in the input layer of the network. In this approach exists an evident separation of roles: the network is responsible for the non-linearity and the memory is responsible for the time. The automatic construction of the neural network architecture is carried out taking into account habituation units. The habituation unit regulates the growing and the pruning of neurons. The procedure of inclusion, adaptation and removal of synaptic connections is carried out in accordance with competitive hebbian learning technique. In many practical problems, as the ones in the robotic area, self-organization, temporal representation and constructive learning are essential factors to the success of the task. The great difficulty and, at the same time, the main contribution of this work consists in the integration of these technologies in a neural network architecture in an efficient way. Some case studies have been elaborated to validate and, mainly, to determine the potentialities and the limitations of the proposed neural model. The experiments comprised simple tasks of pattern classification and temporal segmentation. Preliminary results have shown the good efficiency of the neural model compared to existing connectionist architectures and they have been considered sufficiently satisfactory with regard to the evaluated parameters. This text also presents some theoretical aspects of the cognitive science area, the fundamentals of artificial neural networks, the details of a robotic simulation tool, the conclusions, limitations and possible future works.

abstract: Online discussion forums have become an integral part of education and are large repositories of valuable information. They facilitate exploratory learning by allowing users to review and respond to the work of others and approach learning in diverse ways. This research investigates the different comment semantic features and the effect they have on the quality of a post in a large-scale discussion forum. We survey the relevant literature and employ the key content quality identification features. We then construct comment semantics features and build several regression models to explore the value of comment semantics dynamics. The results reconfirm the usefulness of several essential quality predictors, including time, reputation, length, and editorship. We also found that comment semantics are valuable to shape the answer quality. Specifically, the diversity of comments significantly contributes to the answer quality. In addition, when searching for good quality answers, it is important to look for global semantics dynamics (diversity), rather than observe local differences (disputable content). Finally, the presence of comments shepherd the community to revise the posts by attracting attentions to the posts and eventually facilitate the editing process. / Dissertation/Thesis / Masters Thesis Computer Science 2016

Este trabalho investiga Aprendizado Indutivo de Máquina como função das linguagens de descrição, utilizadas para expressar instancias, conceitos e teoria do domínio. A ampliação do poder de representação do aprendizado proporcional e abordada no contexto de indução construtiva, no domínio de funções booleanas, com a proposta de uma estratégia de composição de atributos denominada root-fringe. Avaliações experimentais dessa e de outras estratégias de construção de novos atributos foram conduzidas e os resultados analisados. Dois métodos de poda, para tratamento de ruídos, em aprendizado de arvores de decisão, foram avaliados num ambiente de indução construtiva e os resultados discutidos. Devido a limitação do aprendizado proposicional, foram investigadas formas de ampliação dos limites do aprendizado, através da ampliação do poder representacional das linguagens de descrição. Foi escolhida Programação Lógica Indutiva - PLI - que e um paradigma de aprendizado indutivo que usa restrições de Lógica de Primeira Ordem como linguagens de descrição. O aprendizado em PLI só é factível quando as linguagens utilizadas estão restritas e é fortemente controlado, caso contrário, o aprendizado em PLI se torna indecidível. A pesquisa em PLI se direcionou a formas de restrição das linguagens de descrição da teoria do domínio e de hipóteses. Três algoritmos que \"traduzem\" a teoria do domínio de sua forma intencional, para extensional, são apresentados. As implementações de dois deles são discutidas. As implementações realizadas deram origem a dois ambientes experimentais de aprendizado: o ambiente proposicional experimental, do qual fazem parte o ambiente experimental construtivo, e o ambiente experimental relacional. / This work investigates Inductive Machine Learning as a function of the description languages employed to express instances, concepts and domain theory. The enlargement of the representational power of propositional learning methods is approached via constructive induction, in the domain of boolean functions, through the proposal of a bias for composing attributes, namely, the bias root-fringe. Experimental evaluation of root-fringe, as well as other biases for constructing new attributes was conducted and the results analyzed. Two pruning methods for decision trees were evaluated in an environment of constructive induction and the results discussed. Due to the limitations of propositional learning, ways of enlarging the limits of the learning process were investigated through enlarging the representational power of the description languages. It was chosen Inductive Logic Programming - ILP - that is an inductive learning paradigm that uses restrictions of First Order Logic as description languages. Learning using ILP is only feasible when the languages are restricted and are strongly controlled; otherwise, learning in ILP becomes undecidible. Research work in ILP was directed towards restricting domain theory and hypotheses description languages. Three algorithms that \"translate\" the intentional expression of a domain theory into its extensional expression are presented. The implementations of two of them are discussed. The implementations gave rise to two experimental learning environments: the propositional environment, which includes the constructive environment, and the relational environment.

O presente trabalho propõe um novo modelo de rede neural artificial voltado a aplicações robóticas, em especial a tarefas de natureza espaço-temporal e de horizonte infinito. Este modelo apresenta três características que o tornam único e que foram tomadas como guia para a sua concepção: auto-organização, representação temporal e aprendizado construtivo. O algoritmo de aprendizagem auto-organizada incorpora todos os mecanismos que são básicos para a auto-organização: competição global, cooperação local e auto-amplificação seletiva. A rede neural é suprida com propriedades dinâmicas através de uma memória de curto prazo. A memória de curto prazo é inserida na estrutura da rede por meio de integradores e diferenciadores, os quais são implementados na camada de entrada da rede. Nesta abordagem existe uma evidente separação de papéis: a rede é responsável pela não-linearidade e a memória é responsável pelo tempo. A construção automática da arquitetura da rede neural é realizada de acordo com uma unidade de habituação. A unidade de habituação regula o crescimento e a poda de neurônios. O procedimento de inclusão, adaptação e remoção de conexões sinápticas é realizado conforme o método de aprendizado hebbiano competitivo. Em muitos problemas práticos, como os existentes na área da robótica, a auto-organização, a representação temporal e o aprendizado construtivo são fatores imprescindíveis para o sucesso da tarefa. A grande dificuldade e, ao mesmo tempo, a principal contribuição deste trabalho consiste em integrar tais tecnologias em uma arquitetura de rede neural artificial de maneira eficiente. Estudos de caso foram elaborados para validar e, principalmente, determinar as potencialidades e as limitações do modelo neural proposto. Os cenários abrangeram tarefas simples de classificação de padrões e segmentação temporal. Os resultados preliminares obtidos demonstraram a eficiência do modelo neural proposto frente às arquiteturas conexionistas existentes e foram considerados bastante satisfatórios com relação aos parâmetros avaliados. No texto são apresentados, também, alguns aspectos teóricos das ciências cognitivas, os fundamentos de redes neurais artificiais, o detalhamento de uma ferramenta de simulação robótica, conclusões, limitações e possíveis trabalhos futuros. / The present work proposes a new artificial neural network model suitable for robotic applications, in special to spatiotemporal tasks and infinite horizon tasks. This model has three characteristics which make it unique and are taken as means to guide its conception: self-organization, temporal representation and constructive learning. The algorithm of self-organizing learning incorporates all the mechanisms that are basic to the self-organization: global competition, local cooperation and selective self-amplification. The neural network is supplied with dynamic properties through a short-term memory. The short-term memory is added in the network structure by means of integrators and differentiators, which are implemented in the input layer of the network. In this approach exists an evident separation of roles: the network is responsible for the non-linearity and the memory is responsible for the time. The automatic construction of the neural network architecture is carried out taking into account habituation units. The habituation unit regulates the growing and the pruning of neurons. The procedure of inclusion, adaptation and removal of synaptic connections is carried out in accordance with competitive hebbian learning technique. In many practical problems, as the ones in the robotic area, self-organization, temporal representation and constructive learning are essential factors to the success of the task. The great difficulty and, at the same time, the main contribution of this work consists in the integration of these technologies in a neural network architecture in an efficient way. Some case studies have been elaborated to validate and, mainly, to determine the potentialities and the limitations of the proposed neural model. The experiments comprised simple tasks of pattern classification and temporal segmentation. Preliminary results have shown the good efficiency of the neural model compared to existing connectionist architectures and they have been considered sufficiently satisfactory with regard to the evaluated parameters. This text also presents some theoretical aspects of the cognitive science area, the fundamentals of artificial neural networks, the details of a robotic simulation tool, the conclusions, limitations and possible future works.

This thesis concerns technology use in distance educations and learning practices related to this use. The research was carried out over the period 2005 to 2009 in Bangladesh and Sri Lanka and has been reported in 6 published papers. The research is situated within the field of Information and Communication Technologies for Development (ICT4D) and within this field e-learning. Education is important for development and for many students in developing countries distance education is often the only option to get educated. The research question is if the use of Information and Communication Technology (ICT) in distance education can contribute to development, and if so, how? This question is explored through two case studies in Sri Lanka and Bangladesh. A variety of data collection methods have been used: interviews, questionnaires, participant observations and document review. The research approach is interpretative and findings are analyzed using Structuration Theory. Initial findings showed that a major challenge for students was the change of learning practices that distance education required. Findings also showed that new constructive learning practices emerged through the use of ICT. For development to take place the learning practices of students are important. Students used to learning practices based on uncritical memorization of facts will not easily take initiatives for change, whereas students used to constructive learning practices will.  Notwithstanding the fact that most students found this transition challenging, it was found that by introducing technology into long-established transmission structures, changes towards constructive learning practices occurred. A major contribution of this thesis is to increase the understanding of how ICT in distance education can facilitate constructive learning practices. By arguing that constructive learning practices are conducive to societal change this finding also has implications for development. The thesis also makes a theoretical contribution by extending Structuration Theory’s applicability in demonstrating its explanatory power in settings where researcher and informants are geographically and socially distant.

This study examines the significance of understanding learners’ learning styles in relation to an educator’s learning style. The study explores the extent to which an educator and learners make provision for learning style flexibility by knowing and understanding their learning styles. There were reasons for being actively involved in the study. I wanted to know my learning style and to know and understand the learning styles of my learners. Action research was used to focus on the significance of learning style flexibility in my teaching practice, with the aim to developing myself as a professional and improving my teaching practice. Action research develops through a selfreflective spiral, consisting of cycle, each with its own steps of planning, acting, observing, reflecting and planning again for further implementation. Action research was critical in helping me to enhance my competencies and the competencies of learners who participated in my study and enabled me to improve in an ongoing, cyclical fashion. The use of qualitative and quantitative research methods helped me to learn and understand my learning style and learners’ learning styles. Herrmann’s Whole Brain Dominance Instrument (HBDI) was used to identify my learning style. To identify learners’ learning styles I used a simplified questionnaire that helped me to understand learners’ thinking preferences according to the four quadrants of Herrmann’s model. Learners’ profiles were identified and indicated that they have didderent profiles. Feedback questionnaires for learners and lecturers were used to dtermine feedback on how I facilitate learning and accommodate learners according to their learning styles, and improve myself professionally. Learning style flexibility is an approach that enhances teaching and learning, including the achievement of complex learning outcomes that includes attitudes and personality traits. Educators should move away from a content-driven learning approach to learner-driven approaches that allow learners to discover and construct knowledge on their own. Learning style flexibility and educational change complement each other. Learning style flexibility is significant in teaching and learning and the professional development of educators. Copyright / Dissertation (MEd)--University of Pretoria, 2012. / Humanities Education / unrestricted

No description available.