Algoritmo Q-learning como estratégia de exploração e/ou explotação para metaheurísticas GRASP e algoritmo genético

Techniques of optimization known as metaheuristics have achieved success in the resolution of many problems classified as NP-Hard. These methods use non deterministic approaches that reach very good solutions which, however, don t guarantee the determination of the global optimum. Beyond the inherent difficulties related to the complexity that characterizes the optimization problems, the metaheuristics still face the dilemma of xploration/exploitation, which consists of choosing between a greedy search and a wider exploration of the solution space. A way to guide such algorithms during the searching of better solutions is supplying them with more knowledge of the problem through the use of a intelligent agent, able to recognize promising regions and also identify when they should diversify the direction of the search. This way, this work proposes the use of Reinforcement Learning technique - Q-learning Algorithm - as exploration/exploitation strategy for the metaheuristics GRASP (Greedy Randomized Adaptive Search Procedure) and Genetic Algorithm. The GRASP metaheuristic uses Q-learning instead of the traditional greedy-random algorithm in the construction phase. This replacement has the purpose of improving the quality of the initial solutions that are used in the local search phase of the GRASP, and also provides for the metaheuristic an adaptive memory mechanism that allows the reuse of good previous decisions and also avoids the repetition of bad decisions. In the Genetic Algorithm, the Q-learning algorithm was used to generate an initial population of high fitness, and after a determined number of generations, where the rate of diversity of the population is less than a certain limit L, it also was applied to supply one of the parents to be used in the genetic crossover operator. Another significant change in the hybrid genetic algorithm is the proposal of a mutually interactive cooperation process between the genetic operators and the Q-learning algorithm. In this interactive/cooperative process, the Q-learning algorithm receives an additional update in the matrix of Q-values based on the current best solution of the Genetic Algorithm. The computational experiments presented in this thesis compares the results obtained with the implementation of traditional versions of GRASP metaheuristic and Genetic Algorithm, with those obtained using the proposed hybrid methods. Both algorithms had been applied successfully to the symmetrical Traveling Salesman Problem, which was modeled as a Markov decision process

Mapa de Conteúdos e Mapa de Dependências:Ferramentas Pedagógicas para uma Metodologia de Planejamento baseada em Objetivos Educacionais e sua Implementação em um Ambiente Virtual de Aprendizagem

Furthered mainly by new technologies, the expansion of distance education has created a demand for tools and methodologies to enhance teaching techniques based on proven pedagogical theories. Such methodologies must also be applied in the so-called Virtual Learning Environments. The aim of this work is to present a planning methodology based on known pedagogical theories which contributes to the incorporation of assessment in the process of teaching and learning. With this in mind, the pertinent literature was reviewed in order to identify the key pedagogical concepts needed to the definition of this methodology and a descriptive approach was used to establish current relations between this conceptual framework and distance education. As a result of this procedure, the Contents Map and the Dependence Map were specified and implemented, two teaching tools that promote the planning of a course by taking into account assessment still in this early stage. Inserted on Moodle, the developed tools were tested in a course of distance learning for practical observation of the involved concepts. It could be verified that the methodology proposed by the above-mentioned tools is in fact helpful in course planning and in strengthening educational assessment, placing the student as central element in the process of teaching and learning

Uma contribuição à solução do problema dos k-servos usando aprendizagem por reforço

Neste trabalho é proposto um novo algoritmo online para o resolver o Problema dos k-Servos (PKS). O desempenho desta solução é comparado com o de outros algoritmos existentes na literatura, a saber, os algoritmos Harmonic e Work Function, que mostraram ser competitivos, tornando-os parâmetros de comparação significativos. Um algoritmo que apresente desempenho eficiente em relação aos mesmos tende a ser competitivo também, devendo, obviamente, se provar o referido fato. Tal prova, entretanto, foge aos objetivos do presente trabalho. O algoritmo apresentado para a solução do PKS é baseado em técnicas de aprendizagem por reforço. Para tanto, o problema foi modelado como um processo de decisão em múltiplas etapas, ao qual é aplicado o algoritmo Q-Learning, um dos métodos de solução mais populares para o estabelecimento de políticas ótimas neste tipo de problema de decisão. Entretanto, deve-se observar que a dimensão da estrutura de armazenamento utilizada pela aprendizagem por reforço para se obter a política ótima cresce em função do número de estados e de ações, que por sua vez é proporcional ao número n de nós e k de servos. Ao se analisar esse crescimento (matematicamente, ) percebe-se que o mesmo ocorre de maneira exponencial, limitando a aplicação do método a problemas de menor porte, onde o número de nós e de servos é reduzido. Este problema, denominado maldição da dimensionalidade, foi introduzido por Belmann e implica na impossibilidade de execução de um algoritmo para certas instâncias de um problema pelo esgotamento de recursos computacionais para obtenção de sua saída. De modo a evitar que a solução proposta, baseada exclusivamente na aprendizagem por reforço, seja restrita a aplicações de menor porte, propõe-se uma solução alternativa para problemas mais realistas, que envolvam um número maior de nós e de servos. Esta solução alternativa é hierarquizada e utiliza dois métodos de solução do PKS: a aprendizagem por reforço, aplicada a um número reduzido de nós obtidos a partir de um processo de agregação, e um método guloso, aplicado aos subconjuntos de nós resultantes do processo de agregação, onde o critério de escolha do agendamento dos servos é baseado na menor distância ao local de demanda

Classificação de padrões através de um comitê de máquinas aprimorado por aprendizagem por reforço

Reinforcement learning is a machine learning technique that, although finding a large number of applications, maybe is yet to reach its full potential. One of the inadequately tested possibilities is the use of reinforcement learning in combination with other methods for the solution of pattern classification problems. It is well documented in the literature the problems that support vector machine ensembles face in terms of generalization capacity. Algorithms such as Adaboost do not deal appropriately with the imbalances that arise in those situations. Several alternatives have been proposed, with varying degrees of success. This dissertation presents a new approach to building committees of support vector machines. The presented algorithm combines Adaboost algorithm with a layer of reinforcement learning to adjust committee parameters in order to avoid that imbalances on the committee components affect the generalization performance of the final hypothesis. Comparisons were made with ensembles using and not using the reinforcement learning layer, testing benchmark data sets widely known in area of pattern classification

Roteamento em Redes de Sensores Sem Fios Com Base Em Aprendizagem Por Reforço

The use of wireless sensor and actuator networks in industry has been increasing past few years, bringing multiple benefits compared to wired systems, like network flexibility and manageability. Such networks consists of a possibly large number of small and autonomous sensor and actuator devices with wireless communication capabilities. The data collected by sensors are sent directly or through intermediary nodes along the network to a base station called sink node. The data routing in this environment is an essential matter since it is strictly bounded to the energy efficiency, thus the network lifetime. This work investigates the application of a routing technique based on Reinforcement Learning s Q-Learning algorithm to a wireless sensor network by using an NS-2 simulated environment. Several metrics like energy consumption, data packet delivery rates and delays are used to validate de proposal comparing it with another solutions existing in the literature

Estudo Comparativo de Métricas de Pontuação para Aprendizagem Estrutural de Redes Bayesianas

Bayesian networks are powerful tools as they represent probability distributions as graphs. They work with uncertainties of real systems. Since last decade there is a special interest in learning network structures from data. However learning the best network structure is a NP-Hard problem, so many heuristics algorithms to generate network structures from data were created. Many of these algorithms use score metrics to generate the network model. This thesis compare three of most used score metrics. The K-2 algorithm and two pattern benchmarks, ASIA and ALARM, were used to carry out the comparison. Results show that score metrics with hyperparameters that strength the tendency to select simpler network structures are better than score metrics with weaker tendency to select simpler network structures for both metrics (Heckerman-Geiger and modified MDL). Heckerman-Geiger Bayesian score metric works better than MDL with large datasets and MDL works better than Heckerman-Geiger with small datasets. The modified MDL gives similar results to Heckerman-Geiger for large datasets and close results to MDL for small datasets with stronger tendency to select simpler network structures

Dificuldades no processo ensino aprendizagem de trigonometria por meio de atividades

This study analyses the difficulties that teachers of high school face in the process of the teaching of trigonometry through activities in a construtivist focus. It contains a review of some publications and dissertations related with the study of trigonometry elaborated in the last years by several authors. It resorts to the study of teaching engineering as an instrument used in the research. It also presents a set of activities which will serve as sample to other teachers of mathematics; and points ways for the overcome of the difficulties found

Números complexos: uma proposta de mudança metodológica para uma aprendizagem significativa no ensino médio

This work presents a proposal of a methodological change to the teaching and learning of the complex numbers in the Secondary education. It is based on the inquiries and difficulties of students detected in the classrooms about the teaching of complex numbers and a questioning of the context of the mathematics teaching - that is the reason of the inquiry of this dissertation. In the searching for an efficient learning and placing the work as a research, it is presented a historical reflection of the evolution of the concept of complex numbers pointing out their more relevant focuses, such as: symbolic, numeric, geometrical and algebraic ones. Then, it shows the description of the ways of the research based on the methodology of the didactic engineering. This one is developed from the utilization of its four stages, where in the preliminary analysis stage, two data surveys are presented: the first one is concerning with the way of presenting the contents of the complex numbers in math textbooks, and the second one is concerning to the interview carried out with High school teachers who work with complex numbers in the practice of their professions. At first, in the analysis stage, it is presented the prepared and organized material to be used in the following stage. In the experimentation one, it is presented the carrying out process that was made with the second year High school students in the Centro Federal de Educação tecnológica do Rio Grande do Norte CEFET-RN. At the end, it presents, in the subsequent and validation stages, the revelation of the obtained results from the observations made in classrooms in the carrying out of the didactic sequence, the students talking and the data collection

A química no ensino médio e a contextualização: a fabricação dos sabões e detergentes como tema gerador de ensino aprendizagem

El conocimiento químico es muy importante a la comprensión de procesos físicos y químicos que nos acercan, por una opción de una vida mejor con calidad, fomentando y acompañando el desarrollo tecnológico. Sin embargo, la formación de un pensamiento químico fruto de un aprendizaje significativo es hoy, en todo el país, un reto paro los educadores de química. Estúdios señalan la contextualización de los contenidos químicos como recurso para promover una interrelación entre conocimientos escolares y hechos/situaciones presentes en el cotidaiano de los alumnos, añadiendo significado a los contenidos escolares, proporcionando a los alumnos un aprendizaje significativo. Con tal objetivo, la siguiente pesquisa se realizó con la intención de contribuir con la enseñanza de química y con el propósito general de proponer un materila didáctico que presentase una forma contextualizada de trabajar algunos conceptos y contenidos fundamentales a la química, con tema generador de la enseãnaza y aprendizaje a la fabricación de jabones y detergentes. Con objetivo de justificar la elección del planteamiento de la contextualización y la elaboración del material didáctico, se hizo una pesquisa acerca de la enseãnaza de química en al red pública de educación y la relación de ésta con los contextos pertenecentes a la realidad de los alumnos. Se observó que la enseñanza de química actual en la red pública de educación es tradicional y descontextualizada. Los resultados de esta pesquisa muestran la necesidad de cámbios la forma de como se enseñan los contenidos químicos. En la segunda parte de la pesquisa, se produjo la elaboración de la unidad didáctica de enseñanza, con el objetivo de promover el aprendizaje significativo de conocimientos químicos a partir del tema de la fabricación de jabones y detergentes. Se observó que el trabajo alcanzó los objetivos propuestos. Una evaluación cualitativa mostró que los alumnos estuvieron más participativos e interesados al estudiar química de esta forma. Relatos y decalraciones de los alumnos también indicaron que hubo un aprendizaje significativo de los contenidos trabajados y que los alumnos son capaces de transferirlos para la comprensión de situaciones reales. Y una evaluación cuantitativa del material nos reveló que 87,09% de los alumnos obtuvieron apuntes iguales o superiores a la media necesaria para la aprobación. Esperamos que hayamos contribuído para mejorar la calidad de la enseñanaza de química y que este trabajo sea solamente un comienzo de una gran jornada

A modelagem matemática como alternativa de ensino e aprendizagem da geometria na educação de jovens e adultos

This is work itself insert in the mathematics education field of the youth and adult education to aim to practitioners of the educational action into the mathematics area performing to with this is teaching kind, adopting to as parameter the Mathematics Molding approach. The motive of the research is to draw up a application proposal of the molding mathematics as teaching and learning geometry alternative in the youth and adult education. The research it develops in three class of the third level (series 5th and 6th) of he youth and adults education in the one school municipal from the Natal outskirts. Its have qualitative nature with participating observation approach, once performing to directly in to research environment as a mathematics teacher of those same classes. We are used questionnaires, lesson notes and analyses of the officials documents as an basis of claim instruments. The results indicates that activity used the mathematic moldings were appreciated the savoir-faire of the student in to knowledge construction process, when search develop to significant learning methods, helping to student build has mathematics connections with other knowledge areas and inside mathematics himself, so much that enlarges your understanding and assist has in your participation in the other socials place, over there propitiate to change in student and teacher posture with relation to mathematic classroom dynamics

Contribuições da investigação em sala de aula para uma aprendizagem das secções cônicas com significado

In this work, the didactical possibilities of investigation use in classroom, through an experience with high school students from Federal Center of Technological Education of Paraíba, as well as the study of conic sections were analysed. In order to fulfill our goals the theoretical conceptions concerning the meaninful learning in conection with the investigation of mathematics history were taken into account. The classroom research occurred by means of activities which encouraged the learner to investigate his own concepts on the conic sections. The results of the proposed activities showed the effectiveness and the efficiency of such a methodology as regards the making up of the required knowledge. They also reveal that the investigation in the classroom guides the ones involved, in this process, to have a wider look at the origins, the methods used and the several representations presented by mathematics that certainly lead, specially the students, to a meaninful learning

A Informática como recurso didático para a aprendizagem de Física no ensino médio

The accomplishment of this work was motivated by our concerns, while teacher of Physics discipline, in the medium teaching and in the higher education, where we have been observing a lot of difficulties in the students' acting, to the they try to give pursuit out to their studies of the classroom, because of the lack of appropriate equipments, or even, of a laboratory where they can put in practice the studied contents. The work aims at to build and to test an educational software that it serves as tool auxiliadora in Physics learning in the Medium Teaching, in the area of electricity, with emphasis in the study of the electrodynamic in resistors. The developed software comes as an alternative to the learning problems, putting the computer science as auxiliary tool, because, besides being an alternative in the middle of the technological expansion, endowed with several resources, it stimulates the significant learning, according to David Ausubel's perspective. A software containing a program destined to the applicability of physics contents in the branch of the electricity is presented as an auxiliary tool, where the student can, not just, to review the contents presented at room, as well as for in practice, through a virtual laboratory, some of these contents, besides testing their knowledge through a bank of discursive subjects. The evaluation of the developed software was made submitting him/it to the professionals' of physics area appreciation. Equally, through continuous evaluations, they were made comparisons among the students' of five different groups acting, in the same school, that you/they were used of the program as tool of his auxiliary learning, and the acting of those that didn't use it

A prática interdisciplinar como estratégia de aprendizagem na formação continuada: uma experiência com professores da área das ciências da natureza

The school is a privileged locus of pedagogical reflection and, therefore, can and must be the best place for the process of continuing graduation for teachers. This process can be very productive if executed with an interdisciplinary group, once interdisciplinarity enables sharing different disciplines and also different personal stories. This study aimed to build a continuing graduation opportunity with an interdisciplinary group of teachers to Natural Sciences area, in a private school in the city of Natal - RN. This opportunity was build using as a tool the elaboration of interdisciplinary class called dialog-lesson. The methodology was in accordance with the principles of the qualitative approach of search-action, and the methodological way consisted of three stages that sought to meet the specific objectives: the definition of multidisciplinarity and interdisciplinarity, which had teachers in the Natural Sciences area; present a proposal that emerged from group discussions, identifying some elements of the limits and possibilities of the activity developed by the group of teachers from the Natural Sciences area. The results showed a studies lack on the subject by teachers and induced the reading and studing the Education legal documents (LDB, PCNEM and OCNEM). The planning of lessons led to the need for meetings that established the process of continuing graduation in exercising at the school. The interdisciplinary practice enable many gains, for example, the cohesion of the teachers, the perception need to constantly update and use of teaching units for planning. But it was also possible to observe limits, such as the difficulty of working with large classes and the danger of the content become superficial. The experience has shown that continuing graduation at school is possible and can be beneficial the use of interdisciplinary groups for this purpose, because it allows the exchange of experiences and pratice reflection of teaching in the itself exercise of this teaching

Um estudo sobre o ensino-aprendizagem das demonstrações matemáticas

Demonstrations are fundamental instruments for Mathematics and, as such, are frequently used by mathematicians, math teachers and students. In fact, demonstrations are part of every Mathematics teaching environment, because Mathematics considers something true when it can be demonstrated. This is in contrast to other fields of knowledge that employ observation and experimentation to validate truth. This dissertation presents a study of the teaching and learning of demonstrations in Mathematics, describing a Teaching Module applied in a course on the Theory of Numbers offered by the Mathematics Department of the Universidade Federal do Rio Grande do Norte for mathematics majors. The objective of the dissertation was to propose and test a Teaching Module that can serve as a model for teaching demonstrations. The Teaching Module consisted of the following five steps: the application of a survey to determine the students‟ profiles and their previous knowledge of mathematical language and techniques of demonstration; the analysis of a series of dialogues containing arguments in everyday language; the investigation and analysis of the structure of some important techniques of demonstration; a written assessment; and, finally, an interview to further verify the principal results of the Teaching Module. The analysis of the data obtained though the classroom activities, written assessments and interviews led to the conclusion that there was a significant amount of assimilation of the issue at the level of relational understanding, (SKEMP, 1980). These instruments verified that the students attained considerable improvement in their use of mathematical language and of the techniques of demonstration presented. Thus, the evidence supports the conclusion that the proposed Teaching Module is an effective means for the teaching/learning of mathematical demonstration and, as such, provides a methodological guide which may lay the foundations for a new approach to this important subject

Dificuldades de aprendizagem em estequiometria: uma proposta de ensino apoiada na modelagem

In order to learn/teach chemistry some themes are relevant, like the stoichiometry, which consists in the study of the weight ratios in the combination of elements and compounds between themselves. This is an underlying subject in the understanding/representation/forethought of chemical reactions. Considering these aspects, our study presents a modeling-based proposal to develop the content of stoichiometry with prospective chemistry teachers. With this aim, we have made a review of literature, which we considered when tried to identify the learning difficulties using both quizzes and pedagogical tests, and then, from those difficulties we could propose a teaching unit for this concept and, consequently the evaluation of our proposal. The participants were chemistry undergraduates at the Universidade Federal do Rio Grande do Norte (UFRN) from assorted levels. As a methodological framework, we rely on the discursive textual analysis to characterize the speech of participants. As main results we observed ideas of appearance or disappearance of matter during chemical transformations, disregard of stoichiometric proportions when using drawings to represent the microscopic level of a reaction and confusion between the magnitude amount of matter and other magnitudes such as mass and volume. The final product is a sequence of instruction, based on the modeling previous research literature , with the goal of improving students ability to articulate the macroscopic and submicroscopic levels of representation of the matter