In this thesis we use computational neural network models to examine the dynamics and functionality of the CA3 region of the mammalian hippocampus. The emphasis of the project is to investigate how the dynamic control structures provided by inhibitory circuitry and cellular modification may effect the CA3 region during the recall of previously stored information. The CA3 region is commonly thought to work as a recurrent auto-associative neural network due to the neurophysiological characteristics found, such as, recurrent collaterals, strong and sparse synapses from external inputs and plasticity between coactive cells. Associative memory models have been developed using various configurations of mathematical artificial neural networks which were first developed over 40 years ago. Within these models we can store information via changes in the strength of connections between simplified model neurons (two-state). These memories can be recalled when a cue (noisy or partial) is instantiated upon the net. The type of information they can store is quite limited due to restrictions caused by the simplicity of the hard-limiting nodes which are commonly associated with a binary activation threshold. We build a much more biologically plausible model with complex spiking cell models and with realistic synaptic properties between cells. This model is based upon some of the many details we now know of the neuronal circuitry of the CA3 region. We implemented the model in computer software using Neuron and Matlab and tested it by running simulations of storage and recall in the network. By building this model we gain new insights into how different types of neurons, and the complex circuits they form, actually work. The mammalian brain consists of complex resistive-capacative electrical circuitry which is formed by the interconnection of large numbers of neurons. A principal cell type is the pyramidal cell within the cortex, which is the main information processor in our neural networks. Pyramidal cells are surrounded by diverse populations of interneurons which have proportionally smaller numbers compared to the pyramidal cells and these form connections with pyramidal cells and other inhibitory cells. By building detailed computational models of recurrent neural circuitry we explore how these microcircuits of interneurons control the flow of information through pyramidal cells and regulate the efficacy of the network. We also explore the effect of cellular modification due to neuronal activity and the effect of incorporating spatially dependent connectivity on the network during recall of previously stored information. In particular we implement a spiking neural network proposed by Sommer and Wennekers (2001). We consider methods for improving associative memory recall using methods inspired by the work by Graham and Willshaw (1995) where they apply mathematical transforms to an artificial neural network to improve the recall quality within the network. The networks tested contain either 100 or 1000 pyramidal cells with 10% connectivity applied and a partial cue instantiated, and with a global pseudo-inhibition.We investigate three methods. Firstly, applying localised disynaptic inhibition which will proportionalise the excitatory post synaptic potentials and provide a fast acting reversal potential which should help to reduce the variability in signal propagation between cells and provide further inhibition to help synchronise the network activity. Secondly, implementing a persistent sodium channel to the cell body which will act to non-linearise the activation threshold where after a given membrane potential the amplitude of the excitatory postsynaptic potential (EPSP) is boosted to push cells which receive slightly more excitation (most likely high units) over the firing threshold. Finally, implementing spatial characteristics of the dendritic tree will allow a greater probability of a modified synapse existing after 10% random connectivity has been applied throughout the network. We apply spatial characteristics by scaling the conductance weights of excitatory synapses which simulate the loss in potential in synapses found in the outer dendritic regions due to increased resistance. To further increase the biological plausibility of the network we remove the pseudo-inhibition and apply realistic basket cell models with differing configurations for a global inhibitory circuit. The networks are configured with; 1 single basket cell providing feedback inhibition, 10% basket cells providing feedback inhibition where 10 pyramidal cells connect to each basket cell and finally, 100% basket cells providing feedback inhibition. These networks are compared and contrasted for efficacy on recall quality and the effect on the network behaviour. We have found promising results from applying biologically plausible recall strategies and network configurations which suggests the role of inhibition and cellular dynamics are pivotal in learning and memory.

L'objectif de la recherche en Intelligence Artificielle (IA) est de répliquer les capacités cognitives humaines au moyen des ordinateurs modernes. Les résultats de ces dernières années semblent annoncer une révolution technologique qui pourrait changer profondément la société. Nous focalisons notre intérêt sur deux aspects cognitifs fondamentaux, l'apprentissage et la mémoire. Les mémoires associatives offrent la possibilité de stocker des éléments d'information et de les récupérer à partir d'une partie de leur contenu, et imitent ainsi la mémoire cérébrale. L'apprentissage profond permet de passer d'une perception analogique du monde extérieur à une représentation parcimonieuse et plus compacte. Dans le chapitre 2, nous présentons une mémoire associative inspirée des réseaux de Willshaw, avec une connectivité contrainte. Cela augmente la performance de récupération des messages et l'efficacité du stockage de l'information.Dans le chapitre 3, une architecture convolutive a été appliquée sur une tâche de lecture de mots partiellement affichés dans des conditions similaires à une étude de psychologie sur des sujets humains. Cette expérimentation montre la similarité de comportement du réseau avec les sujets humains concernant différentes caractéristiques de l'affichage des mots.Le chapitre 4 introduit une méthode de représentation des catégories par des assemblées de neurones dans les réseaux profonds. Pour les problèmes à grand nombre de classes, cela permet de réduire significativement les dimensions d'un réseau.Le chapitre 5 décrit une méthode d'interfaçage des réseaux de neurones profonds non supervisés avec les mémoires associatives à cliques. / The objective of research in Artificial Intelligence (AI) is to reproduce human cognitive abilities by means of modern computers. The results of the last few years seem to announce a technological revolution that could profoundly change society. We focus our interest on two fundamental cognitive aspects, learning and memory. Associative memories offer the possibility to store information elements and to retrieve them using a sub-part of their content, thus mimicking human memory. Deep Learning allows to transition from an analog perception of the outside world to a sparse and more compact representation.In Chapter 2, we present a neural associative memory model inspired by Willshaw networks, with constrained connectivity. This brings an performance improvement in message retrieval and a more efficient storage of information.In Chapter 3, a convolutional architecture was applied on a task of reading partially displayed words under similar conditions as in a former psychology study on human subjects. This experiment put inevidence the similarities in behavior of the network with the human subjects regarding various properties of the display of words.Chapter 4 introduces a new method for representing categories usingneuron assemblies in deep networks. For problems with a large number of classes, this allows to reduce significantly the dimensions of a network.Chapter 5 describes a method for interfacing deep unsupervised networks with clique-based associative memories.

Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática, Estatística e Computação Científica / Made available in DSpace on 2018-08-16T05:02:12Z (GMT). No. of bitstreams: 1 Esmi_Estevao_M.pdf: 1708768 bytes, checksum: 81d1d15b597bdc13e41b87c4847aa2f7 (MD5) Previous issue date: 2010 / Resumo: Redes neurais morfológicas (MNN) são redes neurais artificiais cujos nós executam operações elementares da morfologia matemática (MM). Vários modelos de MNNs e seus respectivos algoritmos de treinamentos têm sido propostos nos últimos anos, incluindo os perceptrons morfológicos(MPs), o perceptron morfológico com dendritos, as memórias associativas morfológicas (fuzzy), as redes neurais morfológicas modulares e as redes neurais de pesos compartilhados e regularizados. Aplicações de MNNs incluem reconhecimento de padrão, previsão de séries temporais, detecção de alvos, auto-localização e processamento de imagens hiperespectrais. Nesta tese, abordamos dois novos modelos de redes neurais morfológicas.O primeiro consiste em uma memória associativa fuzzy denominada KS-FAM, e o segundo representa uma nova versão do perceptron morfológico para problemas de classificação de múltiplas classes, denominado perceptron morfológico com aprendizagem competitiva(MP/CL). Para ambos modelos, investigamos e demonstramos várias propriedades. Em particular para a KS-FAM, caracterizamos as condições para que uma memória seja perfeitamente recordada, assim como a formada saída produzida ao apresentar um padrão de entrada qualquer. Provamos ainda que o algoritmo de treinamento do MP/CL converge em um número finito de passos e que a rede produzida independe da ordem com que os padrões de treinamento são apresentados. Além disso, é garantido que o MP/CL resultante classifica perfeitamente todos os dados de treinamento e não produz regiões de indecisões. Finalmente, comparamos os desempenhos destes modelos com os de outros modelos similares em uma série de experimentos, que incluir e conhecimento de imagens em tons de cinza, para a KS-FAM, e classificação de vários conjuntos de dados disponíveis na internet, para o MP/CL / Abstract: Morphological neural networks (MNN) are artificial neural networks whose hidden neurons perform elementary operations of mathematical morphology (MM). Several particular models of MNNs have been proposed in recent years, including morphological perceptrons (MPs), morphological perceptrons with dendrites, (fuzzy) morphological associative memories, modular morphological neural networks as well as morphological shared-weight and regularization neural networks. Applications of MNNs include pattern recognition, time series prediction, target detection, self-location, and hyper-spectral image processing. In this thesis, we present two new models of morphological neural networks. The first one consists of a fuzzy associative memory called KS-FAM. The second one represents a novel version of the morphological perceptron for classification problems with multiple classes called morphological perceptron with competitive learning(MP/CL). For both KS-FAM and MP/CL models, we investigated and showed several properties. In particular, we characterized the conditions for perfect recall using the KS-FAM as well as the outputs produced upon presentation of an arbitrary input patern. In addition, we proved that the learning algorithm of the MP/CL converges in a finite number of steps and that the results produced after the conclusion of the training phase do not depend on the order in which the training patterns are presented to the network. Moreover, the MP/CL is guaranteed to perfectly classify all training data without generating any regions of indecision. Finaly, we compared the performances of our new models and a range of competing models in terms of a series of experiments in gray-scale image recognition (in case of the KS-FAM) and classification using several well-known datasets that are available on the internet (in case of the MP/CL) / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

Nessa dissertação, é investigado o armazenamento e a recuperação de padrões de forma biologicamente inspirada no cérebro. Os modelos estudados consistiram de redes neurais realimentadas, que tentam modelar certos aspectos dinâmicos do funcionamento do cérebro. Em particular, atenção especial foi dada às Redes Neurais Celulares, que constituem uma versão localmente acoplada do já clássico modelo de Hopfield. Além da análise de estabilidade das redes consideradas, foi realizado um teste com o intuito de avaliar o desempenho de diversos métodos de construção de memórias endereçáveis por conteúdo (memórias associativas) em Redes Neurais Celulares. / In this dissertation we investigate biologically inspired models of pattern storage and retrieval, by means of feedback neural networks. These networks try to model some of the dynamical aspects of brain functioning. The study concentrated in Cellular Neural Networks, a local coupled version of the classical Hopfield model. The research comprised stability analysis of the referred networks, as well as performance tests of various methods for content-addressable (associative) memory design in Cellular Neural Networks.

Orientador: Peter Sussner / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-25T00:54:31Z (GMT). No. of bitstreams: 1 Esmi_Estevao_D.pdf: 1836434 bytes, checksum: 5c3a2879200ff2c7bb59b21e24a173fc (MD5) Previous issue date: 2014 / Resumo: Muitas das memórias associativas fuzzy (FAMs) da literatura correspondem a redes neurais com uma única camada de pesos que armazenam de forma distributiva as informações das associações desejadas. As principais aplicações deste tipo de mémorias associativas são encontradas em sistemas baseados em regras fuzzy. Nesta tese introduzimos a classe de memórias associativas fuzzy-T (T-FAMs) que, em contraste com estes outros modelos, representam redes neurais fuzzy com duas camadas. Caso particulares de T-FAMs, denominadas S-FAMs (duais) e E-FAMs, são baseadas em medidas de subsethood e equivalência fuzzy. Resultados gerais sobre a capacidade de armazenamento e a capacidade de correção de erro das T-FAMs também foram providenciados. Adicionalmente, introduzimos um algoritmo geral de treinamento para T-FAM cuja convergência é sempre garantida. Apresentamos ainda um algoritmo alternativo para treinamento de uma certa classe de E-FAMs que além de ajustar os seus parâmetros também determina automaticamente a topologia da rede. Finalmente, comparamos as taxas de classificação produzidas pelas T-FAMs com alguns classificadores bem conhecidos em diversos problemas de classificação disponíveis na internet. Além disso, aplicamos com sucesso as T-FAMs em um problema de auto-localização de robô móvel baseado em visão / Abstract: Most fuzzy associative memories in the literature correspond to neural networks with a single layer of weights that distributively contains the information about the associations to be stored. The main applications of these types of associative memory can be found in fuzzy rule-base systems. In contrast, we present in this thesis the class of T-fuzzy associative memories (T-FAMs) that represent fuzzy neural networks with two layers. Particular cases of T-FAMs, called (dual) S-FAMs and E-FAMs, are based on fuzzy subsethood and equivalence measures. We provide theoretical results concerning the storage capability and error correction capability of T-FAMs. Furthermore, we introduce a general training algorithm for T-FAM that is guaranteed to converge in a finite numbers of iterations. We also proposed another alternative training algorithm for a certain type of E-FAM that not only adjusts the parameters of the corresponding network but also automatically determines its topology. We compare the classification rates produced by T-FAMs with that ones of some well-known classifiers in several benchmark classification problems that are available on the internet. Finally, we successful apply T-FAM approach to a problem of vision-based selflocalization in mobile robotics / Doutorado / Matematica Aplicada / Doutor em Matemática Aplicada

The replication of human intelligence, learning and reasoning by means of computer algorithms is termed Artificial Intelligence (Al) and the interaction of such algorithms with the physical world can be achieved using robotics. The work described in this thesis investigates the applications of concept learning (an approach which takes its inspiration from biological motivations and from survival instincts in particular) to robot control and path planning. The methodology of concept learning has been applied using learning decision trees (DTs) which induce domain knowledge from a finite set of training vectors which in turn describe systematically a physical entity and are used to train a robot to learn new concepts and to adapt its behaviour. To achieve behaviour learning, this work introduces the novel approach of hierarchical learning and knowledge decomposition to the frame of the reactive robot architecture. Following the analogy with survival instincts, the robot is first taught how to survive in very simple and homogeneous environments, namely a world without any disturbances or any kind of "hostility". Once this simple behaviour, named a primitive, has been established, the robot is trained to adapt new knowledge to cope with increasingly complex environments by adding further worlds to its existing knowledge. The repertoire of the robot behaviours in the form of symbolic knowledge is retained in a hierarchy of clustered decision trees (DTs) accommodating a number of primitives. To classify robot perceptions, control rules are synthesised using symbolic knowledge derived from searching the hierarchy of DTs. A second novel concept is introduced, namely that of multi-dimensional fuzzy associative memories (MDFAMs). These are clustered fuzzy decision trees (FDTs) which are trained locally and accommodate specific perceptual knowledge. Fuzzy logic is incorporated to deal with inherent noise in sensory data and to merge conflicting behaviours of the DTs. In this thesis, the feasibility of the developed techniques is illustrated in the robot applications, their benefits and drawbacks are discussed.

Les mécanismes impliqués dans les troubles cognitifs induits à la suite d’une ischémie cérébrale (IC) demeurent mal compris. En plus du cœur ischémique nécrosé et de la zone de pénombre entourant cette lésion, certaines régions éloignées de la zone ischémique peuvent être fonctionnellement affectées, un phénomène connu sous le nom de «diaschisis». Sachant qu’il existe de fortes interactions fonctionnelles entre l’hippocampe (HPC) et le cortex lors des processus mnésiques, nous avons émis la possibilité que les troubles mnésiques survenant après une IC focale qui préserve l’intégrité de l’HPC, auraient pour origine une perturbation de la connectivité cortico-hippocampique conduisant à un hypofonctionnement hippocampique induit par le phénomène de diaschisis. Afin d’éprouver cette hypothèse, nous avons utilisé le modèle d’occlusion permanente de l'artère cérébrale moyenne chez le rat (OPACM) qui reproduit l’ischémie cérébrale focale humaine. Dans ce modèle, le cortex somato-sensoriel (SS) est endommagé unilatéralement alors que l’intégrité de l’HPC est préservé. Les rats OPACM ont montré une diminution de l’expression du gène c-fos dans l’HPC lors de l'exploration d'un nouvel environnement, indiquant une hypoactivation neuronale. Les rats OPACM ont également présenté une perturbation des mémoires olfactive associative et spatiale lors des tests de transmission sociale de préférence alimentaire (TSPA) et du Barnes maze, respectivement. Afin de confirmer que l’hypofonctionnement hippocampique induit par l’IC résultait d’une réduction des afférences corticales («déactivation») provenant du cortex endommagé, nous avons réalisé des inactivations pharmacologiques spécifiques du cortex SS et ou de l’HPC par injection de lidocaïne ou de CNQX. Ces injections ont induit une hypoactivation hippocampique (réduction du nombre de noyaux Fos-positifs) associée à une perturbation mnésique dans le test de TSPA. L'activité hippocampique chez des rats anesthésiés pendant l’IC ou deux semaines après, ainsi que lors de l’inactivation pharmacologique du cortex SS, a également été examinée par une approche électrophysiologique. Les résultats ont montré une altération de la fréquence d’apparition des «sharp-wave ripples» hippocampiques et révélé une instabilité de la fréquence thêta hippocampique lors de la reperfusion ou deux semaines après IC, ainsi que lors de l’inactivation corticale, suggérant une altération de la dynamique d’interaction entre l’HPC et le cortex. Pris dans leur ensemble, ces résultats identifient le phénomène de diaschisis hippocampique comme un mécanisme crucial impliqué dans l’hypofonctionnement hippocampique et les déficits mnésiques observés après une IC. / The cognitive consequences and the underlying mechanisms leading to cognitive impairments after cerebrovascular occlusive diseases are still unclear. In addition to the infarct zone that suffer the deadly consequence of ischemic stroke, the penumbra surrounding the lesion site and some brain regions more remote to the ischemic areas can be functionally affected by the insult. This phenomenon is referred to as diaschisis. In light of the importance of interactions between hippocampus and cortex during memory processing, we hypothesized that the cognitive impairments observed following focal ischemia could occur in the absence of direct hippocampal insult, possibly via impaired connectivity within cortico-hippocampal networks leading to diaschisis-induced hypofunctioning in specific hippocampal subregions. To examine this possibility, we used the distal middle cerebral artery occlusion (dMCAO) ischemic model in rats which induces restricted cortical infarct in the somatosensory (SS) cortex in the absence of direct hippocampal injury. dMCAO rats exhibited reduced expression of the activity-dependent gene c-fos in the hippocampus when exploring a novel environment, indicating neuronal hypoactivation. Ischemic rats also showed impaired associative olfactory and spatial memory when tested in the social transmission of food preference (STFP) task and the Barnes maze test, respectively. To confirm that the ischemic-induced hippocampal hypofunctioning resulted from reduced afferent inputs (i.e. deactivation) originating in the damaged cortex, we performed region-specific pharmacological inactivation of SS and/or HPC using lidocaine or CNQX. Fos imaging revealed that these treatments induced hippocampal hypoactivation and impaired memory performance as measured in the STFP task. We additionally performed electrophysiological recordings of hippocampal activity in anesthetized rats during acute stroke and two weeks later or after SS cortex inactivation. We found an alteration in the occurrence of sharp-wave ripples associated with instability of theta frequency during reperfusion after stroke and SS cortex inactivation, suggesting an alteration in the dynamics of hippocampal-cortical interactions. Taken collectively, these findings identify hippocampal diaschisis as a crucial mechanism for mediating stroke-induced hippocampal hypofunction and associated memory deficits.

Orientador: Peter Sussner / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matematica, Estatistica e Computação Cientifica / Made available in DSpace on 2018-08-07T23:05:00Z (GMT). No. of bitstreams: 1 Mesquita_MarcosEduardoRibeirodoValle_D.pdf: 1277085 bytes, checksum: 70e93671eb62f360b430f7b81b3c71e3 (MD5) Previous issue date: 2007 / Resumo: Uma Memória Associativa (AM, Associative Memory) é um modelo projetado para armazenar pares de entrada e saída. Sobretudo, uma AM deve ser capaz de recordar uma sida desejada ao mesmo após a apresentação de uma versão incompleta ou destorcida de um padrão de entrada. Essa tese de doutorado discute as Memórias Associativas Morfológicas Nebulosas (FMAMs, Fuzzi Morphological Associative Memories), uma classe de memórias associativas elaboradas para armazenar padrões nebulosas cujos neurÔnios realizam operações elementares da morfologia matemática, i.e., dilatação, erosão, anti-dilatação e anti-erosão. É verificado que os principais modelos de Memória Associativa Nebulosa (FAM, Fuzzy Associative Memory) pertencem à classe das FMAMs. Essa tese introduz as Memórias Associativas Nebulosas Implicativas (IFAMs, Implicative Fuzzy Associative Memories) e suas versões duas com respeito à negação e adjunção. Uma IFAM é uma FMAM onde os pares de entrada e saída são armazenados usando o armazenamento nebuloso implicativo. No armazenamento nebuloso implicativo, os pesos sinápticos. Resultados sobre a fase de armazenamento faz IFAMs e das IFAMs duas são apresentados. Em particular, são demonstrados teoremas sobre a convergência, capacidade de armazenamento, tolerância à ruído e pontos fixos das IFAMs e das IFAMs duais para o caso autoassoplos e resultados teóricos. Finalmente, são apresentadas duas aplicações das FMAMs em problemas de previsão de séries temporais. O primeiro problema trata da previsão da mão-de-obra requerida em industrias metalúrgicas enquanto que a segunda aplicação refere-se a previsão da vazão média mensal da usina hidrelétrica de Furnas / Abstract: Associative memories (AMs) are models that allow for the storage of pattern associations and the retrieval of the desired output pattern upon presentation of a possibly noisy or incomplete version of an input pattern. This thesis discusses fuzzy morphological associative memories (FMAMs), a general class of AMs designed to store fuzzy patterns and described by fuzzy neural networks. Each neuron of a FMAM model performs an elementary operation of mathematical morphology such as dilation, erosion, anti-dilation, and anti-erosion. We show that the most widely known models of fuzzy associative memories (FAMs) belong to the FMAM class. This thesis introduces the implicative fuzzy associative memories (IFAMs) and their dual versions with respect to negation and adjunction. An IFAM is a FMAM model where the patterns are stored by means of implicative fuzzy learning. Specifically, in implicative fuzzy learning, the synaptic weights are given by the minimum of the implication of pre- and postsynaptic activations. We present results concerning the recall and storing phase of IFAM and the dual IFAM models. In particular, we present theorems concerning the convergence, the storage capacity, the noise tolerance, and the fixed points of the IFAM and dual IFAM models in the auto-associative case. We compare the IFAMs with several others FAM models by means of theoretical results and examples. Finally, we present two applications of FMAM models in problems of time-series prediction. The first problem concerns the engineering manpower requirement in steel manufacturing industry while the second refers to the stream flow prediction of a large hydroelectric plant, namely Furnas / Doutorado / Doutor em Matemática Aplicada

Orientador: Peter Sussner / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-26T17:27:37Z (GMT). No. of bitstreams: 1 Schuster_Tiago_M.pdf: 2910336 bytes, checksum: 1f5147831dd6410a0fdb0c0fa53d94c8 (MD5) Previous issue date: 2015 / Resumo: As últimas décadas têm testemunhado a emergência de uma variedade de abordagens à resolução de problemas com base na computação em reticulados como, por exemplo, as redes neurais morfológicas e os modelos neurocomputação e de raciocínio fuzzy em reticulados. Usamos aqui o termo "reticulado'' no sentido dado no trabalho seminal de Birkhoff. A teoria dos reticulados nasceu da álgebra booleana e tem um grande leque de aplicações como a análise de conceitos formais, a inteligência computacional, a teoria dos conjuntos fuzzy e a morfologia matemática (MM). A MM em reticulados completos representa a base teórica para uma série de modelos de inteligência computacional conhecidos como redes neurais morfológicas (MNNs), que incluem as memórias associativas morfológicas em tons de cinza e as memórias associativas morfológicas fuzzy (FMAMs). As últimas décadas têm testemunhado a emergência de uma variedade de abordagens à resolução de problemas com base na computação em reticulados como, por exemplo, as redes neurais morfológicas e os modelos neurocomputação e de raciocínio fuzzy em reticulados. Usamos aqui o termo "reticulado'' no sentido dado no trabalho seminal de Birkhoff. A teoria dos reticulados nasceu da álgebra booleana e tem um grande leque de aplicações como a análise de conceitos formais, a inteligência computacional, a teoria dos conjuntos fuzzy e a morfologia matemática (MM). A MM em reticulados completos representa a base teórica para uma série de modelos de inteligência computacional conhecidos como redes neurais morfológicas (MNNs), que incluem as memórias associativas morfológicas em tons de cinza e as memórias associativas morfológicas fuzzy (FMAMs). O advento de sistemas fuzzy tipo-2 sugere o desenvolvimento das FMAMs tipo-2 e em particular FMAMs tipo-2 intervalar, ou FMAMs intervalar (IV-FMAMs). Observemos aqui que a classe dos conjuntos fuzzy, assim como a dos conjuntos fuzzy tipo-2, fuzzy tipo-2 intervalar e fuzzy intervalar sobre um universo arbitrário em conjunção com diferentes escolhas de ordens parciais formam classes de conjuntos L-fuzzy, em que L denota um reticulado completo. Nessa dissertação de mestrado, introduzimos as memórias associativas L-fuzzy (L-FMAMs) com base na morfologia matemática L-fuzzy (L-FMM). Nosso foco está nas FMAMs fuzzy intervalar, uma vez que sistemas fuzzy intervalar têm sido aplicados com sucesso em problemas de engenharia, computação com palavras e raciocínio aproximado. Nós aplicamos os modelos de IV-FMAMs em conjunção com a técnica de clusterização fuzzy c-means intervalar a um problema de predição de série temporal, especificamente o prognóstico da vazão mensal de uma usina hidroelétrica localizada no sudeste brasileiro. Por fim, comparamos as predições produzidas pela abordagem das IV-FMAMs com aquelas produzidas por modelos competitivos da literatura / Abstract: The last decade has witnessed the emergence of a variety of lattice computing approaches towards computational intelligence such as morphological neural networks and fuzzy lattice reasoning / neuro-computing models. Here, the technical term "lattice" refers to a lattice in the mathematical sense of Birkhoff's seminal work. Lattice theory grew out of Boolean algebra and has found a wide range of applications such as mathematical morphology, formal concept analysis, computational intelligence, and fuzzy set theory. Mathematical morphology on complete lattices represents the theoretical basis for a range of computational intelligence models known as morphological neural networks (MNNs) including gray-scale and fuzzy morphological associative memories (FMAMs). The advent of type-2 fuzzy systems suggests the development of type-2 FMAMs and in particular interval type-2 FMAMs or interval-valued FMAMs. Recall that the class of fuzzy sets as well as the classes of type-2, interval type-2, and interval-valued fuzzy sets over an arbitrary universe together with different choices of partial orderings form classes of L-fuzzy sets, where L denotes a complete lattice. In this master's thesis, we introduce L-fuzzy morphological associative memories (L-FMAMs) on the basis of L-FMM. Our focus is on interval-valued FMAMs since interval type-2 fuzzy systems, have found various applications in engineering, computing with words, and approximate reasoning. We applied the aforementioned interval-valued FMAM models in conjunction with the interval-valued fuzzy c-means clustering technique to a time-series prediction problem in industry, namely the problem of forecasting the average monthly streamflow of a hydroelectric plant located in southeastern Brazil, and compared the predictions produced by the IV-FMAM approach with the ones produced by a number of competitive models from the literature / Mestrado / Matematica Aplicada / Mestre em Matemática Aplicada

This paper inspired by simulation by Artificial Neural Networks (ANNs) applied recently for evaluation of phonics methodology to teach children "how to read". A novel approach for teaching a mathematical topic using a computer aided learning (CAL) package applied at educational field (a children classroom). Interesting practical results obtained after field application of suggested CAL package with and without associated teacher''s voice. Presented study highly recommends application of a novel teaching trend based on behaviorism and individuals'' learning styles. That is to improve quality of children mathematical learning performance.