Background: Expertise retrieval is an information retrieval technique that focuses on techniques to identify the most suitable ’expert’ for a task from a list of individuals. Objectives: This master thesis is a collaboration with Volvo Cars to attempt applying this concept and match employees based on information that was extracted from an internal tool of the company. In this tool, the employees describe themselves in free-flowing text. This text is extracted from the tool and analyzed using Natural Language Processing (NLP) techniques. Methods: Through the course of this project, various techniques are employed and experimented with to study, analyze and understand the unlabelled textual data using NLP techniques. Through the course of the project, we try to match individuals based on information extracted from these techniques using Unsupervised MachineLearning methods (K-means clustering).Results. The results obtained from applying the various NLP techniques are explained along with the algorithms that are implemented. Inferences deduced about the properties of the data and methodologies are discussed. Conclusions: The results obtained from this project have shown that it is possible to extract patterns among people based on free-text data written about them. The future aim is to incorporate the semantic relationship between the words to be able to identify people who are similar and dissimilar based on the data they share about themselves.

Ballstering appartient à la famille des méthodes de machine learning qui ont pour but de regrouper en classes les éléments formant la base de données étudiée et ce sans connaissance au préalable des classes qu'elle contient. Ce type de méthodes, dont le représentant le plus connu est k-means, se rassemblent sous le terme de "partitionnement de données" ou "clustering". Récemment un algorithme de partitionnement "Fast Density Peak Clustering" (FDPC) paru dans le journal Science a suscité un intérêt certain au sein de la communauté scientifique pour son aspect innovant et son efficacité sur des données distribuées en groupes non-concentriques. Seulement cet algorithme présente une complexité telle qu'il ne peut être aisément appliqué à des données volumineuses. De plus nous avons pu identifier plusieurs faiblesses pouvant nuire très fortement à la qualité de ses résultats, dont en particulier la présence d'un paramètre général dc difficile à choisir et ayant malheureusement un impact non-négligeable. Compte tenu de ces limites, nous avons repris l'idée principale de FDPC sous un nouvel angle puis apporté successivement des modifications en vue d'améliorer ses points faibles. Modifications sur modifications ont finalement donné naissance à un algorithme bien distinct que nous avons nommé Ballstering. Le fruit de ces 3 années de thèse se résume principalement en la conception de ce dernier, un algorithme de partitionnement dérivé de FDPC spécialement conçu pour être efficient sur de grands volumes de données. Tout comme son précurseur, Ballstering fonctionne en deux phases: une phase d'estimation de densité suivie d'une phase de partitionnement. Son élaboration est principalement fondée sur la construction d'une sous-procédure permettant d'effectuer la première phase de FDPC avec une complexité nettement amoindrie tout évitant le choix de dc qui devient dynamique, déterminé suivant la densité locale. Nous appelons ICMDW cette sous-procédure qui représente une partie conséquente de nos contributions. Nous avons également remanié certaines des définitions au cœur de FDPC et revu entièrement la phase 2 en s'appuyant sur la structure arborescente des résultats fournis par ICDMW pour finalement produire un algorithme outrepassant toutes les limitations que nous avons identifié chez FDPC. / Ballstering belongs to the machine learning methods that aim to group in classes a set of objects that form the studied dataset, without any knowledge of true classes within it. This type of methods, of which k-means is one of the most famous representative, are named clustering methods. Recently, a new clustering algorithm "Fast Density Peak Clustering" (FDPC) has aroused great interest from the scientific community for its innovating aspect and its efficiency on non-concentric distributions. However this algorithm showed a such complexity that it can't be applied with ease on large datasets. Moreover, we have identified several weaknesses that impact the quality results and the presence of a general parameter dc difficult to choose while having a significant impact on the results. In view of those limitations, we reworked the principal idea of FDPC in a new light and modified it successively to finally create a distinct algorithm that we called Ballstering. The work carried out during those three years can be summarised by the conception of this clustering algorithm especially designed to be effective on large datasets. As its Precursor, Ballstering works in two phases: An estimation density phase followed by a clustering step. Its conception is mainly based on a procedure that handle the first step with a lower complexity while avoiding at the same time the difficult choice of dc, which becomes automatically defined according to local density. We name ICMDW this procedure which represent a consistent part of our contributions. We also overhauled cores definitions of FDPC and entirely reworked the second phase (relying on the graph structure of ICMDW's intermediate results), to finally produce an algorithm that overcome all the limitations that we have identified.

La tomographie par émission de positrons (TEP) est une technique d'imagerie nucléaire noninvasive qui permet de quantifier les fonctions métaboliques des organes à partir de la diffusion d'un radiotraceur injecté dans le corps. Alors que l'imagerie statique est souvent utilisée afin d'obtenir une distribution spatiale de la concentration du traceur, une meilleure évaluation de la cinétique du traceur est obtenue par des acquisitions dynamiques. En ce sens, la TEP dynamique a suscité un intérêt croissant au cours des dernières années, puisqu'elle fournit des informations à la fois spatiales et temporelles sur la structure des prélèvements de traceurs en biologie \textit{in vivo}. Les techniques de quantification les plus efficaces en TEP dynamique nécessitent souvent une estimation de courbes temps-activité (CTA) de référence représentant les tissus ou une fonction d'entrée caractérisant le flux sanguin. Dans ce contexte, de nombreuses méthodes ont été développées pour réaliser une extraction non-invasive de la cinétique globale d'un traceur, appelée génériquement analyse factorielle. L'analyse factorielle est une technique d'apprentissage non-supervisée populaire pour identifier un modèle ayant une signification physique à partir de données multivariées. Elle consiste à décrire chaque voxel de l'image comme une combinaison de signatures élémentaires, appelées \textit{facteurs}, fournissant non seulement une CTA globale pour chaque tissu, mais aussi un ensemble des coefficients reliant chaque voxel à chaque CTA tissulaire. Parallèlement, le démélange - une instance particulière d'analyse factorielle - est un outil largement utilisé dans la littérature de l'imagerie hyperspectrale. En imagerie TEP dynamique, elle peut être très pertinente pour l'extraction des CTA, puisqu'elle prend directement en compte à la fois la non-négativité des données et la somme-à-une des proportions de facteurs, qui peuvent être estimées à partir de la diffusion du sang dans le plasma et les tissus. Inspiré par la littérature de démélange hyperspectral, ce manuscrit s'attaque à deux inconvénients majeurs des techniques générales d'analyse factorielle appliquées en TEP dynamique. Le premier est l'hypothèse que la réponse de chaque tissu à la distribution du traceur est spatialement homogène. Même si cette hypothèse d'homogénéité a prouvé son efficacité dans plusieurs études d'analyse factorielle, elle ne fournit pas toujours une description suffisante des données sousjacentes, en particulier lorsque des anomalies sont présentes. Pour faire face à cette limitation, les modèles proposés ici permettent un degré de liberté supplémentaire aux facteurs liés à la liaison spécifique. Dans ce but, une perturbation spatialement variante est introduite en complément d'une CTA nominale et commune. Cette variation est indexée spatialement et contrainte avec un dictionnaire, qui est soit préalablement appris ou explicitement modélisé par des non-linéarités convolutives affectant les tissus de liaisons non-spécifiques. Le deuxième inconvénient est lié à la distribution du bruit dans les images PET. Même si le processus de désintégration des positrons peut être décrit par une distribution de Poisson, le bruit résiduel dans les images TEP reconstruites ne peut généralement pas être simplement modélisé par des lois de Poisson ou gaussiennes. Nous proposons donc de considérer une fonction de coût générique, appelée $\beta$-divergence, capable de généraliser les fonctions de coût conventionnelles telles que la distance euclidienne, les divergences de Kullback-Leibler et Itakura-Saito, correspondant respectivement à des distributions gaussiennes, de Poisson et Gamma. Cette fonction de coût est appliquée à trois modèles d'analyse factorielle afin d'évaluer son impact sur des images TEP dynamiques avec différentes caractéristiques de reconstruction. / Thanks to its ability to evaluate metabolic functions in tissues from the temporal evolution of a previously injected radiotracer, dynamic positron emission tomography (PET) has become an ubiquitous analysis tool to quantify biological processes. Several quantification techniques from the PET imaging literature require a previous estimation of global time-activity curves (TACs) (herein called \textit{factors}) representing the concentration of tracer in a reference tissue or blood over time. To this end, factor analysis has often appeared as an unsupervised learning solution for the extraction of factors and their respective fractions in each voxel. Inspired by the hyperspectral unmixing literature, this manuscript addresses two main drawbacks of general factor analysis techniques applied to dynamic PET. The first one is the assumption that the elementary response of each tissue to tracer distribution is spatially homogeneous. Even though this homogeneity assumption has proven its effectiveness in several factor analysis studies, it may not always provide a sufficient description of the underlying data, in particular when abnormalities are present. To tackle this limitation, the models herein proposed introduce an additional degree of freedom to the factors related to specific binding. To this end, a spatially-variant perturbation affects a nominal and common TAC representative of the high-uptake tissue. This variation is spatially indexed and constrained with a dictionary that is either previously learned or explicitly modelled with convolutional nonlinearities affecting non-specific binding tissues. The second drawback is related to the noise distribution in PET images. Even though the positron decay process can be described by a Poisson distribution, the actual noise in reconstructed PET images is not expected to be simply described by Poisson or Gaussian distributions. Therefore, we propose to consider a popular and quite general loss function, called the $\beta$-divergence, that is able to generalize conventional loss functions such as the least-square distance, Kullback-Leibler and Itakura-Saito divergences, respectively corresponding to Gaussian, Poisson and Gamma distributions. This loss function is applied to three factor analysis models in order to evaluate its impact on dynamic PET images with different reconstruction characteristics.

Machine learning enables machines to learn automatically from data. In literature, graph-based methods have received increasing attention due to their ability to learn from both local and global information. In these methods, each data instance is represented by a vertex and is linked to other vertices according to a predefined affinity rule. However, they usually have unfeasible time cost for large problems. To overcome this problem, techniques can employ a heuristic to find suboptimal solutions in a feasible time. Early heuristic optimization methods exploit nature-inspired collective processes, such as ants looking for food sources and swarms of bees. Nowadays, advances in the field of complex systems provide powerful tools to assess and to understand dynamical systems. Complex networks, which are graphs with nontrivial topology, are among these theoretical tools capable of describing the interplay of topology, structure, and dynamics of complex systems. Therefore, machine learning methods based on complex networks and collective dynamics have been proposed. They encompass three steps. First, a complex network is constructed from the input data. Then, the simulation of a distributed collective system in the network generates rich information. Finally, the collected information is used to solve the learning problem. The coordination of the individuals in the system permit to achieve dynamics that is far more complex than the behavior of single individuals. In this research, I have explored collective dynamics in machine learning tasks, both in unsupervised and semi-supervised scenarios. Specifically, I have proposed a new collective system of competing particles that shifts the traditional vertex-centric dynamics to a more informative edge-centric one. Moreover, it is the first particle competition system applied in machine learning task that has deterministic behavior. Results show several advantages of the edge-centric model, including the ability to acquire more information about overlapping areas, a better exploration behavior, and a faster convergence time. Also, I have proposed a new network formation technique that is not based on similarity and has low computational cost. Since addition and removal of samples in the network is cheap, it can be used in real-time application. Finally, I have conducted analytical investigations of a flocking-like system that was needed to guarantee the expected behavior in community detection tasks. In conclusion, the result of the research contributes to many areas of machine learning and complex systems. / Aprendizado de máquina permite que computadores aprendam automaticamente dos dados. Na literatura, métodos baseados em grafos recebem crescente atenção por serem capazes de aprender através de informações locais e globais. Nestes métodos, cada item de dado é um vértice e as conexões são dadas uma regra de afinidade. Todavia, tais técnicas possuem custo de tempo impraticável para grandes grafos. O uso de heurísticas supera este problema, encontrando soluções subótimas em tempo factível. No início, alguns métodos de otimização inspiraram suas heurísticas em processos naturais coletivos, como formigas procurando por comida e enxames de abelhas. Atualmente, os avanços na área de sistemas complexos provêm ferramentas para medir e entender estes sistemas. Redes complexas, as quais são grafos com topologia não trivial, são uma das ferramentas. Elas são capazes de descrever as relações entre topologia, estrutura e dinâmica de sistemas complexos. Deste modo, novos métodos de aprendizado baseados em redes complexas e dinâmica coletiva vêm surgindo. Eles atuam em três passos. Primeiro, uma rede complexa é construída da entrada. Então, simula-se um sistema coletivo distribuído na rede para obter informações. Enfim, a informação coletada é utilizada para resolver o problema. A interação entre indivíduos no sistema permite alcançar uma dinâmica muito mais complexa do que o comportamento individual. Nesta pesquisa, estudei o uso de dinâmica coletiva em problemas de aprendizado de máquina, tanto em casos não supervisionados como semissupervisionados. Especificamente, propus um novo sistema de competição de partículas cuja competição ocorre em arestas ao invés de vértices, aumentando a informação do sistema. Ainda, o sistema proposto é o primeiro modelo de competição de partículas aplicado em aprendizado de máquina com comportamento determinístico. Resultados comprovam várias vantagens do modelo em arestas, includindo detecção de áreas sobrepostas, melhor exploração do espaço e convergência mais rápida. Além disso, apresento uma nova técnica de formação de redes que não é baseada na similaridade dos dados e possui baixa complexidade computational. Uma vez que o custo de inserção e remoção de exemplos na rede é barato, o método pode ser aplicado em aplicações de tempo real. Finalmente, conduzi um estudo analítico em um sistema de alinhamento de partículas. O estudo foi necessário para garantir o comportamento esperado na aplicação do sistema em problemas de detecção de comunidades. Em suma, os resultados da pesquisa contribuíram para várias áreas de aprendizado de máquina e sistemas complexos.

Redes neurais pulsadas - redes que utilizam uma codificação temporal da informação - têm despontado como uma nova e promissora abordagem dentro do paradigma conexionista emergente da ciência cognitiva. Um desses novos modelos é a rede neural pulsada de base radial, capaz de armazenar informação nos tempos de atraso axonais dos neurônios e que comporta algoritmos explícitos de treinamento. A recente proposição de uma sistemática para a codificação temporal dos dados de entrada utilizando campos receptivos gaussianos tem apresentado interessantes resultados na tarefa do agrupamento de dados (clustering). Este trabalho propõe uma função para o aprendizado não supervisionado dessa rede, com o objetivo de simplificar a sistemática de calibração de alguns dos seus parâmetros-chave, aprimorando a convergência da rede neural pulsada no aprendizado baseado em instâncias. O desempenho desse modelo é avaliado na tarefa de classificação de padrões, particularmente na classificação de pixels em imagens coloridas no domínio da visão computacional. / Pulsed neural networks - networks that encode information in the timing of spikes - have been studied as a new and promising approach in the artificial neural networks paradigm, emergent from cognitive science. One of these new models is the pulsed neural network with radial basis function, a network able to store information in the axonal propagation delay of neurons. Recently, a new method for encoding input-data by population code using gaussian receptive fields has showed interesting results in the clustering task. The present work proposes a function for the unsupervised learning task in this network, which goal includes the simplification of the calibration of the network key parameters and the enhancement of the pulsed neural network convergence to instance based learning. The performance of this model is evaluated for pattern classification, particularly for the pixel colors classification task, in the computer vision domain.

Le corps humain compte plus de 200 types cellulaires différents possédant une copie identique du génome mais exprimant un ensemble différent de gènes. Le contrôle de l'expression des gènes est assuré par un ensemble de mécanismes de régulation agissant à différentes échelles de temps et d'espace. Plusieurs maladies ont pour cause un dérèglement de ce système, notablement les certains cancers, et de nombreuses applications thérapeutiques, comme la médecine régénérative, reposent sur la compréhension des mécanismes de la régulation géniques. Ce travail de thèse propose, dans une première partie, un algorithme d'annotation (GABI) pour identifier les motifs récurrents dans les données de séquençage haut-débit. La particularité de cet algorithme est de prendre en compte la variabilité observée dans les réplicats des expériences en optimisant le taux de faux positif et de faux négatif, augmentant significativement la fiabilité de l'annotation par rapport à l'état de l'art. L'annotation fournit une information simplifiée et robuste à partir d'un grand ensemble de données. Appliquée à une base de données sur l'activité des régulateurs dans l'hématopoieïse, nous proposons des résultats originaux, en accord avec de précédentes études. La deuxième partie de ce travail s'intéresse à l'organisation 3D du génome, intimement lié à l'expression génique. Elle est accessible grâce à des algorithmes de reconstruction 3D à partir de données de contact entre chromosomes. Nous proposons des améliorations à l'algorithme le plus performant du domaine actuellement, ShRec3D, en permettant d'ajuster la reconstruction en fonction des besoins de l'utilisateur. / The human body has more than 200 different cell types each containing an identical copy of the genome but expressing a different set of genes. The control of gene expression is ensured by a set of regulatory mechanisms acting at different scales of time and space. Several diseases are caused by a disturbance of this system, notably some cancers, and many therapeutic applications, such as regenerative medicine, rely on understanding the mechanisms of gene regulation. This thesis proposes, in a first part, an annotation algorithm (GABI) to identify recurrent patterns in the high-throughput sequencing data. The particularity of this algorithm is to take into account the variability observed in experimental replicates by optimizing the rate of false positive and false negative, increasing significantly the annotation reliability compared to the state of the art. The annotation provides simplified and robust information from a large dataset. Applied to a database of regulators activity in hematopoiesis, we propose original results, in agreement with previous studies. The second part of this work focuses on the 3D organization of the genome, intimately linked to gene expression. This structure is now accessible thanks to 3D reconstruction algorithm from contact data between chromosomes. We offer improvements to the currently most efficient algorithm of the domain, ShRec3D, allowing to adjust the reconstruction according to the user needs.

nÃo hà / Esta dissertaÃÃo tem como principal meta realizar um estudo comparativo do desempenho de algoritmos de redes neurais competitivas nÃo-supervisionadas em problemas de quantizaÃÃo vetorial (QV) e aplicaÃÃes correlatas, tais como anÃlise de agrupamentos (clustering) e compressÃo de imagens. A motivaÃÃo para tanto parte da percepÃÃo de que hà uma relativa escassez de estudos comparativos sistemÃticos entre algoritmos neurais e nÃo-neurais de anÃlise de agrupamentos na literatura especializada. Um total de sete algoritmos sÃo avaliados, a saber: algoritmo K -mÃdias e as redes WTA, FSCL, SOM, Neural-Gas, FuzzyCL e RPCL. De particular interesse à a seleÃÃo do nÃmero Ãtimo de neurÃnios. NÃo hà um mÃtodo que funcione para todas as situaÃÃes, restando portanto avaliar a influÃncia que cada tipo de mÃtrica exerce sobre algoritmo em estudo. Por exemplo, os algoritmos de QV supracitados sÃo bastante usados em tarefas de clustering. Neste tipo de aplicaÃÃo, a validaÃÃo dos agrupamentos à feita com base em Ãndices que quantificam os graus de compacidade e separabilidade dos agrupamentos encontrados, tais como Ãndice Dunn e Ãndice Davies-Bouldin (DB). Jà em tarefas de compressÃo de imagens, determinado algoritmo de QV à avaliado em funÃÃo da qualidade da informaÃÃo reconstruÃda, daà as mÃtricas mais usadas serem o erro quadrÃtico mÃdio de quantizaÃÃo (EQMQ) ou a relaÃÃo sinal-ruÃdo de pico (PSNR). Empiricamente verificou-se que, enquanto o Ãndice DB favorece arquiteturas com poucos protÃtipos e o Dunn com muitos, as mÃtricas EQMQ e PSNR sempre favorecem nÃmeros ainda maiores. Nenhuma das mÃtricas supracitadas leva em consideraÃÃo o nÃmero de parÃmetros do modelo. Em funÃÃo disso, esta dissertaÃÃo propÃe o uso do critÃrio de informaÃÃo de Akaike (AIC) e o critÃrio do comprimento descritivo mÃnimo (MDL) de Rissanen para selecionar o nÃmero Ãtimo de protÃtipos. Este tipo de mÃtrica mostra-se Ãtil na busca do nÃmero de protÃtipos que satisfaÃa simultaneamente critÃrios opostos, ou seja, critÃrios que buscam o menor erro de reconstruÃÃo a todo custo (MSE e PSNR) e critÃrios que buscam clusters mais compactos e coesos (Ãndices Dunn e DB). Como conseqÃÃncia, o nÃmero de protÃtipos obtidos pelas mÃtricas AIC e MDL à geralmente um valor intermediÃrio, i.e. nem tÃo baixo quanto o sugerido pelos Ãndices Dunn e DB, nem tÃo altos quanto o sugerido pelas mÃtricas MSE e PSNR. Outra conclusÃo importante à que nÃo necessariamente os algoritmos mais sofisticados do ponto de vista da modelagem, tais como as redes SOM e Neural-Gas, sÃo os que apresentam melhores desempenhos em tarefas de clustering e quantizaÃÃo vetorial. Os algoritmos FSCL e FuzzyCL sÃo os que apresentam melhores resultados em tarefas de quantizaÃÃo vetorial, com a rede FSCL apresentando melhor relaÃÃo custo-benefÃcio, em funÃÃo do seu menor custo computacional. Para finalizar, vale ressaltar que qualquer que seja o algoritmo escolhido, se o mesmo tiver seus parÃmetros devidamente ajustados e seus desempenhos devidamente avaliados, as diferenÃas de performance entre os mesmos sÃo desprezÃveis, ficando como critÃrio de desempate o custo computacional. / The main goal of this master thesis was to carry out a comparative study of the performance of algorithms of unsupervised competitive neural networks in problems of vector quantization (VQ) tasks and related applications, such as cluster analysis and image compression. This study is mainly motivated by the relative scarcity of systematic comparisons between neural and nonneural algorithms for VQ in specialized literature. A total of seven algorithms are evaluated, namely: K-means, WTA, FSCL, SOM, Neural-Gas, FuzzyCL and RPCL. Of particular interest is the problem of selecting an adequate number of neurons given a particular vector quantization problem. Since there is no widespread method that works satisfactorily for all applications, the remaining alternative is to evaluate the influence that each type of evaluation metric has on a specific algorithm. For example, the aforementioned vector quantization algorithms are widely used in clustering-related tasks. For this type of application, cluster validation is based on indexes that quantify the degrees of compactness and separability among clusters, such as the Dunn Index and the Davies- Bouldin (DB) Index. In image compression tasks, however, a given vector quantization algorithm is evaluated in terms of the quality of the reconstructed information, so that the most used evaluation metrics are the mean squared quantization error (MSQE) and the peak signal-to-noise ratio (PSNR). This work verifies empirically that, while the indices Dunn and DB or favors architectures with many prototypes (Dunn) or with few prototypes (DB), metrics MSE and PSNR always favor architectures with well bigger amounts. None of the evaluation metrics cited previously takes into account the number of parameters of the model. Thus, this thesis evaluates the feasibility of the use of the Akaikeâs information criterion (AIC) and Rissanenâs minimum description length (MDL) criterion to select the optimal number of prototypes. This type of evaluation metric indeed reveals itself useful in the search of the number of prototypes that simultaneously satisfies conflicting criteria, i.e. those favoring more compact and cohesive clusters (Dunn and DB indices) versus those searching for very low reconstruction errors (MSE and PSNR). Thus, the number of prototypes suggested by AIC and MDL is generally an intermediate value, i.e nor so low as much suggested for the indexes Dunn and DB, nor so high as much suggested one for metric MSE and PSNR. Another important conclusion is that sophisticated models, such as the SOM and Neural- Gas networks, not necessarily have the best performances in clustering and VQ tasks. For example, the algorithms FSCL and FuzzyCL present better results in terms of the the of the reconstructed information, with the FSCL presenting better cost-benefit ratio due to its lower computational cost. As a final remark, it is worth emphasizing that if a given algorithm has its parameters suitably tuned and its performance fairly evaluated, the differences in performance compared to others prototype-based algorithms is minimum, with the coputational cost being used to break ties.

Redes neurais pulsadas - redes que utilizam uma codificação temporal da informação - têm despontado como uma nova e promissora abordagem dentro do paradigma conexionista emergente da ciência cognitiva. Um desses novos modelos é a rede neural pulsada de base radial, capaz de armazenar informação nos tempos de atraso axonais dos neurônios e que comporta algoritmos explícitos de treinamento. A recente proposição de uma sistemática para a codificação temporal dos dados de entrada utilizando campos receptivos gaussianos tem apresentado interessantes resultados na tarefa do agrupamento de dados (clustering). Este trabalho propõe uma função para o aprendizado não supervisionado dessa rede, com o objetivo de simplificar a sistemática de calibração de alguns dos seus parâmetros-chave, aprimorando a convergência da rede neural pulsada no aprendizado baseado em instâncias. O desempenho desse modelo é avaliado na tarefa de classificação de padrões, particularmente na classificação de pixels em imagens coloridas no domínio da visão computacional. / Pulsed neural networks - networks that encode information in the timing of spikes - have been studied as a new and promising approach in the artificial neural networks paradigm, emergent from cognitive science. One of these new models is the pulsed neural network with radial basis function, a network able to store information in the axonal propagation delay of neurons. Recently, a new method for encoding input-data by population code using gaussian receptive fields has showed interesting results in the clustering task. The present work proposes a function for the unsupervised learning task in this network, which goal includes the simplification of the calibration of the network key parameters and the enhancement of the pulsed neural network convergence to instance based learning. The performance of this model is evaluated for pattern classification, particularly for the pixel colors classification task, in the computer vision domain.

Over the last decade, data has become a highly valuable resource. Electrical power grids deal with large quantities of data, and continuously collect this for analytical purposes. Anomalies that occur within this data is important to identify since they could cause nonoptimal performance within the substations, or in worse cases damage to the substations themselves. However, large datasets in the order of millions are hard or even impossible to gain a reasonable overview of the data manually. When collecting data from electrical power grids, predefined triggering criteria are often used to indicate that an event has occurred within the specific system. This makes it difficult to search for events that are unknown to the operator of the deployed acquisition system. Clustering, an unsupervised machine learning method, can be utilised for fault prediction within systems generating large amounts of multivariate time-series data without labels and can group data more efficiently and without the bias of a human operator. A large number of clustering techniques exist, as well as methods for extracting information from the data itself, and identification of these was of utmost importance. This thesis work presents a study of the methods involved in the creation of such a clustering system which is suitable for the specific type of data. The objective of the study was to identify methods that enables finding the underlying structures of the data and cluster the data based on these. The signals were split into multiple frequency sub-bands and from these features could be extracted and evaluated. Using suitable combinations of features the data was clustered with two different clustering algorithms, CLARA and CLARANS, and evaluated with established quality analysis methods. The results indicate that CLARA performed overall best on all the tested feature sets. The formed clusters hold valuable information such as indications of unknown events within the system, and if similar events are clustered together this can assist a human operator further to investigate the importance of the clusters themselves. A further conclusion from the results is that research into the use of more optimised clustering algorithms is necessary so that expansion into larger datasets can be considered.

Diese Doktorarbeit führt ein hierarchisches Modell für das unüberwachte Lernen aus quasi-natürlichen Videosequenzen ein. Das Modell basiert auf den Lernprinzipien der Langsamkeit und Spärlichkeit, für die verschiedene Ansätze und Implementierungen vorgestellt werden. Eine Vielzahl von Neuronentypen im Hippocampus von Nagern und Primaten kodiert verschiedene Aspekte der räumlichen Umgebung eines Tieres. Dazu gehören Ortszellen (place cells), Kopfrichtungszellen (head direction cells), Raumansichtszellen (spatial view cells) und Gitterzellen (grid cells). Die Hauptergebnisse dieser Arbeit basieren auf dem Training des hierarchischen Modells mit Videosequenzen aus einer Virtual-Reality-Umgebung. Das Modell reproduziert die wichtigsten räumlichen Codes aus dem Hippocampus. Die Art der erzeugten Repräsentationen hängt hauptsächlich von der Bewegungsstatistik des simulierten Tieres ab. Das vorgestellte Modell wird außerdem auf das Problem der invaranten Objekterkennung angewandt, indem Videosequenzen von simulierten Kugelhaufen oder Fischen als Stimuli genutzt wurden. Die resultierenden Modellrepräsentationen erlauben das unabhängige Auslesen von Objektidentität, Position und Rotationswinkel im Raum. / This thesis introduces a hierarchical model for unsupervised learning from naturalistic video sequences. The model is based on the principles of slowness and sparseness. Different approaches and implementations for these principles are discussed. A variety of neuron classes in the hippocampal formation of rodents and primates codes for different aspects of space surrounding the animal, including place cells, head direction cells, spatial view cells and grid cells. In the main part of this thesis, video sequences from a virtual reality environment are used for training the hierarchical model. The behavior of most known hippocampal neuron types coding for space are reproduced by this model. The type of representations generated by the model is mostly determined by the movement statistics of the simulated animal. The model approach is not limited to spatial coding. An application of the model to invariant object recognition is described, where artificial clusters of spheres or rendered fish are presented to the model. The resulting representations allow a simple extraction of the identity of the object presented as well as of its position and viewing angle.