Submitted by Erika Demachki (erikademachki@gmail.com) on 2015-11-18T17:19:21Z No. of bitstreams: 2 Dissertação - Juliana Rodrigues - 2007.pdf: 1538909 bytes, checksum: 0a976b8281558b7da7e02c2b92b427c2 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Erika Demachki (erikademachki@gmail.com) on 2015-11-18T17:56:19Z (GMT) No. of bitstreams: 2 Dissertação - Juliana Rodrigues - 2007.pdf: 1538909 bytes, checksum: 0a976b8281558b7da7e02c2b92b427c2 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2015-11-18T17:56:19Z (GMT). No. of bitstreams: 2 Dissertação - Juliana Rodrigues - 2007.pdf: 1538909 bytes, checksum: 0a976b8281558b7da7e02c2b92b427c2 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2007-03-28 / Periphyton algae community on slides glasses at Água Limpa River and Lake of Tigres (Britânia, State of Goiás, Brazil) during two low waters periods. The aims of this dissertation was analyze the community of periphytic algae of Lake of Tigres (15°36"33,1''S/ 51º17'55,7''W) and Agua Limpa river (15°36"33,5''S / 51º17'56,3'' W ). Both environment belong the Tocantins-Araguaia basin and have differents water hydrodynamics. The first one is a blocked valley. This study looking for the influence of differents day of artificial substratum disposed in differents moths of low water periods (dry and beginning of the rain periods) in the first chapter and colonization during four weeks in dry period of 2005 in the second one. Were collected informations about climatic variables (temperature of air, pH, conductivity, turbidity, total dissolved solids, dissolved oxygen, total nitrogen and total phosphorous). The synthesis of limmnologicals variables was made by principal components analysis (PCA) and the synthesis of limnological and periphyton algae community were made by canonical correspondence analysis (CCA) and dissimilarity analysis (WPGMA) In the firs part of the study (2004) the artificial substratum were exposed during 20 until 37 days, both environments studied had high level of dissolved oxygen and water temperature, low level of nutrients and pH between alkaline and acid. Still had 67 taxa the majority was microperiphytics and ordinary species, high diversity and density tendency the β diversity had tendency to be homogeneous. The diatoms, R and S-selected taxa group were predominant in both sample stations. Only two species were dominant taxa (Navícula sp1- A1; Pinularia flexuosa - N2) and 34 were abundant. CCA characterized phosphorous and R-estratgist algae and Pseudoanabaena sp1, Surirella sp2, Oedogonium sp1, Cosmarium sp1, Cosmarium sp4 e Diploneis subovalis how the most important descriptors of the community of periphytic algae. In 2005, the artificial substratum that were exposed only in Agua Limpa River during four weeks and removed in 4th , 6th , 8th , 17th and 30th days, the water had high level of oxygen, nutrients and water temperature. Were registered 121 taxa, the majority micoperiphytic, ordinary species and diatoms. Were found high density and specific diversity. The β diversity was homogeneous specific composition, 72 abundant species, R and S-selected taxa group, and diatoms were representatives during the study, especially in richness and density. Both samples stations had same specific composition and functional group because de very closes geographic area. At the end of the study were detected the principal explanations of the periphyton algae community were made by R and S-selected taxa of functional group, Bacillariophyceae, high diversity and density and Total phosphorous. / Comunidade de algas perifíticas em substrato artificial no rio Água Limpa e lago dos Tigres (Britânia-Go) durante dois períodos de águas baixas - O Lago dos Tigres (15°36"33,1''S/ 51º17'55,7''W) e o rio Água Limpa (15°36"33,5''S/51º17'56,3''W) fazem parte da bacia Tocantins-Araguaia, região Oeste do Estado de Goiás. Este lago é um vale bloqueado formado pelo barramento do rio Água limpa pelo rio Vermelho. Encontra-se em uma região agropecuarista sob forte pressão antrópica. Até o presente, nenhum estudo sobre o perifiton foi desenvolvido nestes ambientes. Este trabalho teve como objetivo caracterizar a estrutura e dinâmica da comunidade de algas perifíticas entre uma região lótica (Rio Água Limpa- Estação 1) e outra região lêntica (Lagos dos Tigres – Estação 2) em 2004 e em região lótica em 2005 (Margem direita – Estação 1 e Margem esquerda – Estação 2), verificar se existem diferenças na estrutura de comunidade entre os dois ambientes com relação ao tempo de exposição de substrato artificial aos diferentes regimes hidrológicos em 2004 e ainda analisar o processo de colonização em substrato artificial durante um período de seca de 2005 no Rio Água Limpa. As coletas de 2004 foram realizadas no período de águas baixas (julho a setembro – seca; outubro a novembro – início de chuva), inicialmente com a instalação de armadilhas para o ficoperifiton e posterior recolhimento em diferentes períodos, mas dentro da maturidade da comunidade (entre 20 e 37 dias). As coletas de 2005 foram realizadas em quatro semanas de período seco, sendo que após a instalação o substrato artificical foi recolhido nos 4o, 6o, 8o,17o e 30o dias de colonização. As variáveis climáticas (temperatura do ar, precipitação, vento), morfométricas (profundidade, largura) e as limnológicas (transparência, pH, condutividade, temperatura da água, turbidez, sólidos totais dissolovidos, oxigênio dissolvido, nitrogênio total e fósforo total) foram analisados em todos os períodos amostrais. O diagnóstico das tendências temporais das variáveis limnologicas foram efetuadas através de Análise de Componente Principais (ACP) e a síntese dessas variáveis com a comunidade ficoperifitica foram efetuadas por meio de Análise de Correspondência Canônica (ACC). Efetuou-se para amostragens de 2004 uma Análise de Dissimilaridade (WPGMA). Em 2004, a avaliaçao da comunidade em substratos artificiais retirados em diferentes espaços de tempo (em regiões lótica e lêntica) mostrou os seguintes resultados: ambas estações apresentaram acentuados níveis de oxigênio, baixos teores de nutrientes (nitrogênio e fósoforo total), pH variou de levemente ácido a levemente alcalino e temperatura da água praticamente homogênea ao longo do período estudado. A comunidade ficoperifítica do rio Água Limpa e lago dos Tigres apresentou apenas 67 táxons (maioria microperifíticas), a maioria dos táxons foram classificados como comuns quanto a frequencia de ocorrência, diversidade específica foi elevada e diversidade beta tendendo a ser mais homogênea ao final do estudo indicando que nesses locais está ocorrendo a estabilidade da composição floristica da comunidade ficoperifitica. Entre rio de lago em relação aos dois períodos estudados não houve heterogeneidade, pois a riqueza e a densidade foram semelhantes entre as duas estações. Ocorreram apenas duas espécies dominantes (Navícula sp1- A1; Pinularia flexuosa - N2) e 34 abundantes no sistema. A ACC caracterizou a variável limnológica fósforo total como provavelmente importante na instalação de algas de estratégia R em ambas estações. Os grupos funcionais de estrategias S e R predominaram provavelmente favorecido pelo fóforo total conforme indica a ACC. A classe Bacillariphyceae (Navícula sp1. Gomphonema truncatum, Fragilaria capuccina var. fragilarioides, Bacillariophyceae sp1) foi a mais representativa durante todo o período amostral tanto em densidade quanto em riqueza específica. O rio Água Limpa e o lago dos Tigres não apresentaram diferença entre si de acordo com a composição florística, classes taxonômicas e grupos funcionais. Quando realizado um estudo de colonização da comunidade ficoperifítica no rio Água Limpa em quatro semanas do período de seca de 2005 observou-se que as águas do rio apresentaram acentuados níveis de oxigênio, elevados teores de nutrientes (nitrogênio e fósforo total), pH ácido e temperatura da água elevada praticamente homogênea ao longo do período estudado. Foram registrados 121 táxons, a maioria espécies microperifiticas e de freqüência comum composta principalmente por diatomáceas. O ambiente estudado apresentou densidade e diversidade específica elevada e diversidade beta tendendo a uma composição florística homogênea ao final do estudo. Os valores de densidade foram elevados e ocorreram 72 espécies abundantes. Fósforo total foi provavelmente importante para a instalação de algas perifíticas com estratégia R em ambas estações. Os grupos funcionais de estratégia R (Pseudoanabaena sp1,Cosmarium sp1, Cosmarium sp4 e Diploneis subovalis) e S (Surirella sp2), e foram provavelmente favorecidos pelo fósforo conforme indicou a ACC. A presença de Bacillariophyceae foi mais representativa durante todo o período amostral, tanto em número de táxons quanto em densidade. As duas estações tiveram praticamente a mesma composição florística e grupos funcionais, em decorrência da proximidade geográfica. Ao final do estudo destaca-se a importância de baixa transparência e valores de fósforo total um pouco elevados beneficiando Bacillariophyceae, grupos funcionais de estratégias R e S, elevadas densidades e diversidade específica nos dois períodos analisados (2004 e 2005) e o fósforo total como variável limnológica mais importante durante as duas etapas deste estudo.

Esta dissertação apresenta o aperfeiçoamento de um sistema de tradução automática português-inglês. Nosso objetivo principal é criar regras de transferência estrutural entre o par de línguas português e inglês e avaliar, através do uso da métrica de avaliação METEOR, o desempenho do sistema. Para isto, utilizamos um corpus teste criado especialmente para esta pesquisa. Tendo como ponto de partida a relevância de uma correta tradução para os tempos verbais de uma sentença, este trabalho priorizou a criação de regras que tratassem a transferência entre os tempos verbais do português brasileiro para o inglês americano. Devido ao fato de os verbos em português estarem distribuídos por três conjugações, criamos um corpus para cada uma dessas conjugações. O objetivo da criação desses corpora é verificar a aplicação das regras de transferência estrutural entre os tempos verbais em todas as três classes de conjugação. Após a criação dos corpora, mapeamos os tempos verbais em português no modo indicativo, subjuntivo e imperativo para os tempos verbais do inglês. Em seguida, iniciamos a construção das regras de transferência estrutural entre os tempos verbais mapeados. Ao final da construção das regras, submetemos os corpora obedecendo as três classes de conjugação à métrica de avaliação automática METEOR. Os resultados da avaliação do sistema após a inserção das regras apresentaram uma regressão quando comparado a avaliação do sistema no estágio inicial da pesquisa. Detectamos, através de análises dos resultados, que a métrica de avaliação automática METEOR não foi sensível às modificações feitas no sistema, embora as regras criadas sigam a gramática tradicional da língua portuguesa e estejam sendo aplicadas a todas as três classes de conjugação. Apresentamos em detalhes o conjunto de regras sintáticas e os corpora utilizados neste estudo, e que acreditamos serem de utilidade geral para quaisquer sistemas de tradução automática entre o português brasileiro e o inglês americano. Outra contribuição deste trabalho está em discutir os valores apresentados pela métrica METEOR e sugerir que novos ajustes sejam feitos a esses parâmetros utilizados pela métrica. / This dissertation presents the development of a Portuguese-to-English Machine Translation system. Our main objective is creating structural transfer rules between this pair of languages, and evaluate the performance of the system using the METEOR evaluation metric. Therefore, we developed a corpus to enable this study. Taking translation relevance as a starting point, we focused on verbal tenses and developed rules that dealt with transfer between verbal tenses from the Brazilian Portuguese to US English. Due to the fact that verbs in Portuguese are distributed in three conjugations, we created one corpus for each of these conjugations. The objective was to verify the application of structural transfer rules between verbal tenses in each conjugation class in isolation. After creating these corpora, we mapped the Portuguese verbal tenses in the indicative, subjunctive and imperative modes to English. Next, we constructed structural transfer rules to these mapped verbal tenses. After constructing these rules, we evaluated our corpora using the METEOR evaluation metric. The results of this evaluation showed lack of improvement after the insertion of these transfer rules, when compared to the initial stage of the system. We detected that the METEOR evaluation metric was not sensible to these modi_cations made to the system, even though they were linguistically sound and were being applied correctly to the sentences. We introduce in details the set of transfer rules and corpora used in this study, and we believe they are general enough to be useful in any rule-based Portuguese-to-English Machine Translation system. Another contribution of this work lies in the discussion of the results presented by the METEOR metric. We suggest adjustments to be made to its parameters, in order to make it more sensible to sentences variation such as those introduced by our rules.

This final thesis covers the basics of artificial neural networks, with focus on supervised learning, pruning and the problem of achieving good generalization ability. An empirical investigation is conducted on twelve dierent problems originating from the Proben1 benchmark collection.The results indicate that pruning is more likely to improve generalization if the data is sensitive to overtting or if the networks are likely to be trapped in local minima.

Ce mémoire eut pour ambition première d’aborder les enjeux éthiques de la robotique sexuelle selon une perspective critique féministe. Nous avons défendu la thèse selon laquelle les robotes sexuelles telles que développées à ce jour constituaient le continuum de la domination masculine en contexte sexuel. Il s’agissait alors dans un premier temps de distinguer les fondements sur lesquels la robotique sexuelle prenait forme, à savoir une structure de pouvoir inégalitaire, l’utilisation de normes dominantes et des schémas relationnels oppressifs. Dans un deuxième temps, il s’agissait de mettre en lumière les implications symboliques, c’est-à-dire au niveau de la représentation du groupe des femmes et matérielles, autrement dit en ce qui concerne le renforcement des inégalités de statuts, nous amenant alors à déterminer les caractéristiques propres à la robotique sexuelle, en d’autres termes, la réitération de paradigmes de domination sous une forme novatrice, soit celle d’un.e robot.e intelligent.e. / The primary aim of this paper was to address the ethical issues of sexual robotics from a feminist critical perspective. We argued that sexual robotes as developed to date constituted the continuum of male domination in a sexual context. The first step was to distinguish the foundations on which sexual robotics was taking shape, namely an unequal power structure, the use of dominant norms and oppressive relational patterns. The second step was to highlight the symbolic implications, that is to say the representation of women’s group and material effects, in other words, the reinforcement of inequalities of status. This led us to determine the characteristics of sexual robotics, otherwise stated, the repetition of domination paradigms in an innovative form, that of an intelligent robot.

Object detection on natural images has become a single-stage end-to-end process thanks to recent breakthroughs on deep neural networks. By contrast, automated pulmonary nodule detection is usually a three steps method: lung segmentation, generation of nodule candidates and false positive reduction. This project tackles the nodule detection problem with a single stage modelusing a deep neural network. Pulmonary nodules have unique shapes and characteristics which are not present outside of the lungs. We expect the model to capture these characteristics and to only focus on elements inside the lungs when working on raw CT scans (without the segmentation). Nodules are small, distributed and infrequent. We show that a well trained deep neural network can spot relevantfeatures and keep a low number of region proposals without any extra preprocessing or post-processing. Due to the visual nature of the task, we designed a three-dimensional convolutional neural network with residual connections. It was inspired by the region proposal network of the Faster R-CNN detection framework. The evaluation is performed on the LUNA16 dataset. The final score is 0.826 which is the average sensitivity at 0.125, 0.25, 0.5, 1, 2, 4, and 8 false positives per scan. It can be considered as an average score compared to other submissions to the challenge. However, the solution described here was trained end-to-end and has fewer trainable parameters. / Objektdetektering i naturliga bilder har reducerates till en enstegs process tack vare genombrott i djupa neurala nätverk. Automatisk detektering av pulmonella nodulärer är vanligtvis ett trestegsproblem: segmentering av lunga, generering av nodulärkandidater och reducering av falska positiva utfall. Det här projektet tar sig an nodulärdetektering med en enstegsmodell med hjälp av ett djupt neuralt nätverk. Pulmonella nodulärer har unika karaktärsdrag som inte finns utanför lungorna. Modellen förväntas fånga dessa drag och enbart fokusera på element inuti lungorna när den arbetar med datortomografibilder. Nodulärer är små och glest föredelade. Vi visar att ett vältränat nätverk kan finna relevanta särdrag samt föreslå ett lågt antal intresseregioner utan extra för- eller efter- behandling. På grund av den visuella karaktären av det här problemet så designade vi ett tredimensionellt s.k. convolutional neural network med residualkopplingar. Projektet inspirerades av Faster R-CNN, ett nätverk som utmärker sig i sin förmåga att detektera intresseregioner. Nätverket utvärderades på ett dataset vid namn LUNA16. Det slutgiltiga nätverket testade 0.826, vilket är genomsnittlig sensitivitet vid 0.125, 0.25, 0.5, 1, 2, 4, och 8 falska positiva per utvärdering. Detta kan anses vara genomsnittligt jämfört med andra deltagande i tävlingen, men lösningen som föreslås här är en enstegslösning som utför detektering från början till slut och har färre träningsbara parametrar. / La détection d’objets sur les images naturelles est devenue au fil du temps un processus réalisé de bout en bout en une seule étape grâce aux évolutions récentes des architectures de neurones artificiels profonds. En revanche, la détection automatique de nodules pulmonaires est généralement un processus en trois étapes : la segmentation des poumons (pré-traitement), la génération de zones d’intérêt (modèle) et la réduction des faux positifs (post-traitement). Ce projet s’attaque à la détection des nodules pulmonaires en une seule étape avec un réseau profond de neurones artificiels. Les nodules pulmonaires ont des formes et des structures uniques qui ne sont pas présentes en dehors de cet organe. Nous nous attendons à ce qu’un modèle soit capable de capturer ces caractéristiques et de se focaliser uniquement sur les éléments à l’intérieur des poumons alors même qu’il reçoit des images brutes (sans segmentation des poumons). Les nodules sont petits, peu fréquents et répartis aléatoirement. Nous montrons qu’un modèle correctement entraîné peut repérer les éléments caractéristiques des nodules et générer peu de localisations sans pré-traitement ni post-traitement. Du fait de la nature visuelle de la tâche, nous avons développé un réseau neuronal convolutif tridimensionnel. L’architecture utilisée est inspirée du méta-algorithme de détection Faster R-CNN. L’évaluation est réalisée avec le jeu de données du challenge LUNA16. Le score final est de 0.826 qui représente la sensibilité moyenne pour les valeurs de 0.125, 0.25, 0.5, 1, 2, 4 et 8 faux positifs par scanner. Il peut être considéré comme un score moyen comparé aux autres contributions du challenge. Cependant, la solution décrite montre la faisabilité d’un modèle en une seule étape, entraîné de bout en bout. Le réseau comporte moins de paramètres que la majorité des solutions.

Lung cancer is the most commonly diagnosed cancer in the world and its finding is mainly incidental. New technologies and more specifically artificial intelligence has lately acquired big interest in the medical field as it can automate or bring new information to the medical staff. Many research have been done on the detection or classification of lung cancer. These works are done on local region of interest but only a few of them have been done looking at a full CT-scan. The aim of this thesis was to assess lung damages from CT images using new machine learning methods. First, single predictors had been learned by a 3D resnet architecture: cancer, emphysema, and opacities. Emphysema was learned by the network reaching an AUC of 0.79 whereas cancer and opacity predictions were not really better than chance AUC = 0.61 and AUC = 0.61. Secondly, a multi-task network was used to predict the factors altogether. A training with no prior knowledge and a transfer learning approach using self-supervision were compared. The transfer learning approach showed similar results in the multi-task approach for emphysema with AUC=0.78 vs 0.60 without pre-training and opacities with an AUC=0.61. Moreover using the pre-training approach enabled the network to reach the same performance as each of single factor predictor but with only one multi-task network which saves a lot of computational time. Finally a risk score can be derived from the training to use this information in a clinical context.

University/College selection is a daunting task for young adults and their parents alike. This research presents True-Ed Select, a machine learning framework that simplifies the college selection process. The framework uses a four-layered approach including the user survey, machine learning, consolidation, and recommendation. The first layer collects both the objective and subjective attributes from users that best characterize their ideal college experience. The second layer employs machine learning techniques to analyze the objective and subjective attributes. The third layer combines the results from the machine learning techniques. The fourth layer inputs the consolidated result and presents a user-friendly list of top educational institutions that best match the user’s interests. We use our framework to analyze over 3500 United States post-secondary institutions and show search space reduction to top 20 institutions. This drastically reduced search space facilitates effective and assured college selection for end users. Our survey results with 10 participants highlight an average satisfaction rating of 4.11, showing the efficacy of the framework.

This essay proves the Universal Approximation Theorem for discriminatory activation functions, in particular continuous sigmoidal functions, over compact spaces. In other words, a neural network with a discriminatory activation function can approximate any continuous function over a compact space. The theorem guarantees the effectivity of neural networks. / Denna uppsats bevisar Universala Approximations Satsen för diskriminerande funktioner, särskillt kontinuerliga sigmoidala funktioner, över kompakta rum. Med andra ord, ett neuralt nätverk med en discriminerande aktiveringsfunktion kan approximera alla kontinguerliga functioner över kompakta rum. Satsen garanterar effektivitet av neurala nätverk.

Nesta dissertação nós revisamos a teoria básica que descreve a junção Josephson bosônica para uma e duas espécies partindo do modelo de Bose-Hubbard. Em seguida explicamos como é possível gerar campos de calibe artificiais em um sistema de átomos neutros, como é o caso do condensado de Bose-Einstein. Finalmente, utilizando os conhecimentos teóricos desenvolvidos anteriormente nós buscamos os estados estacionários de um sistema de pseudospin 1/2 submetido a um campo de calibre não-Abeliano artificial, que torna a dinâmica da junção muito mais complexa e rica. Nós também exploramos um novo desbalanceamento de população que surge no sistema, devido a presença do campo de calibre, com características similares as do Macroscopic Quantum Self-Trapping. / In this dissertation we review the basic theory that describes the bosonic Josephson junction for one and two species using the Bose-Hubbard model. Afterwards, we explain how it is possible to generate artificial gauge fields for neutral atoms, like a Bose-Einstein condensate. Finally, using this theoretical background we search for stationary states of a pseudospin 1/2 system subject to a non-Abelian artificial gauge field which turns the dynamic of the junction much more complex and rich. We also explore a possible new populational imbalance that appears on the system due to the presence of the gauge field, with similar features as the Macroscopic Quantum Self-Trapping.

Dans cette thèse, nous présentons des modèles appartenant au domaine de l’intelligence artificielle afin de prédire l’indice magnétique global am à partir des paramètres du vent solaire. Ceci est fait dans l’optique de fournir des modèles opérationnels basés sur les données enregistrées par le satellite ACE situé au point de Lagrange L1. L’indice am ne possède pas à l’heure actuelle de modèles de prédiction. Pour prédire cet indice, nous avons fait appel à des modèles non-linéaires que sont les réseaux de neurones, permettant de modéliser le comportement complexe et non-linéaire de la magnétosphère terrestre. Nous avons dans un premier temps travaillé sur le développement et l’optimisation des modèles de réseaux classiques comme le perceptron multi-couche. Ces modèles ont fait leurs preuves en météorologie spatiale pour prédire aussi bien des indices magnétiques spécifiques à des systèmes de courant comme l’indice Dst, caractéristique du courant annulaire, que des indices globaux comme l’indice Kp. Nous avons en particulier étudié un réseau temporel appelé Time Delay Neural Network (TDNN) et évalué sa capacité à prédire l’indice magnétique am à une heure, uniquement à partir des paramètres du vent solaire. Nous avons analysé la sensibilité des performances des réseaux de neurones en considérant d’une part les données fournies par la base OMNI au niveau de l’onde de choc, et d’autre part des données obtenues par le satellite ACE en L1. Après avoir étudié la capacité de ces réseaux à prédire am, nous avons développé un réseau de neurones encore jamais utilisé en météorologie spatiale, le réseau Long Short Term Mermory ou LSTM. Ce réseau possède une mémoire à court et à long terme, et comme le TDNN, fournit des prédictions de l’indice am uniquement à partir des paramètres du vent solaire. Nous l’avons optimisé afin de modéliser au mieux le comportement de la magnétosphère et avons ainsi obtenu de meilleures performances de prédiction de l'indice am par rapport à celles obtenues avec le TDNN. Nous avons souhaité continuer le développement et l’optimisation du LSTM en travaillant sur l’utilisation de fonctions de couplage en entrée de ce réseau de neurones, et sur le développement de réseaux multisorties pour prédire les indices magnétiques am sectoriels ou aσ, spécifiques à chaque secteur Temps Magnétique Local. Enfin, nous avons développé une nouvelle technique combinant réseau LSTM et processus gaussiens, afin de fournir une prédiction probabiliste jusqu’à six heures des indices magnétiques Dst et am. Cette méthode a été dans un premier temps développée pour l’indice magnétique Dst afin de pouvoir comparer les performances du modèle hybride à des modèles de référence, puis appliquée à l’indice magnétique am. / In this thesis, we present models which belongs to the field of artificial intelligence to predict the geomagnetic index am based on solar wind parameters. This is done in terms to provide operational models based on data recorded by the ACE satellite located at the Lagrangian point L1. Currently, there is no model providing predictions of the geomagnetic index am. To predict this index, we have relied on nonlinear models called neural networks, allowing to model the complex and nonlinear dynamic of the Earth’s magnetosphere. First, we have worked on the development and the optimisation of basics neural networks like the multilayer perceptron. These models have proven in space weather to predict geomagnetic index specific to current systems like the Dst index, characteristic of the ring current, as well as the global geomagnetic index Kp. In particular, we have studied a temporal network, called the Time Delay Neural Network (TDNN) and we assessed its ability to predict the geomagnetic index am within one hour, base only on solar wind parameters. We have analysed the sensitivity of neural network performance when considering on one hand data from the OMNI database at the bow shock, and on the other hand data from the ACE satellite at the L1 point. After studying the ability of neural networks to predict the geomagnetic index am, we have developped a neural network which has never been used before in Space Weather, the Long Short Term Memory or LSTM. Like the TDNN, this network provides am prediction based only on solar wind parameters. We have optimised this network to model at best the magnetosphere behaviour and obtained better performance than the one obtained with the TDNN. We continued the development and the optimisation of the LSTM network by using coupling functions as neural network features, and by developing multioutput networks to predict the sectorial am also called aσ, specific to each Magnetical Local Time sector. Finally, we developped a brand new technique combining the LSTM network and gaussian process, to provide probabilistic predictions up to six hours ahead of geomagnetic index Dst and am. This method has been first developped to predict Dst to be able to compare the performance of this model with reference models, and then applied to the geomagnetic index am.