Dissertations / Theses on the topic 'Author and Document Representation Learning'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 38 dissertations / theses for your research on the topic 'Author and Document Representation Learning.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Terreau, Enzo. "Apprentissage de représentations d'auteurs et d'autrices à partir de modèles de langue pour l'analyse des dynamiques d'écriture." Electronic Thesis or Diss., Lyon 2, 2024. http://www.theses.fr/2024LYO20001.
The recent and massive democratization of digital tools has empowered individuals to generate and share information on the web through various means such as blogs, social networks, sharing platforms, and more. The exponential growth of available information, mostly textual data, requires the development of Natural Language Processing (NLP) models to mathematically represent it and subsequently classify, sort, or recommend it. This is the essence of representation learning. It aims to construct a low-dimensional space where the distances between projected objects (words, texts) reflect real-world distances, whether semantic, stylistic, and so on.The proliferation of available data, coupled with the rise in computing power and deep learning, has led to the creation of highly effective language models for word and document embeddings. These models incorporate complex semantic and linguistic concepts while remaining accessible to everyone and easily adaptable to specific tasks or corpora. One can use them to create author embeddings. However, it is challenging to determine the aspects on which a model will focus to bring authors closer or move them apart. In a literary context, it is preferable for similarities to primarily relate to writing style, which raises several issues. The definition of literary style is vague, assessing the stylistic difference between two texts and their embeddings is complex. In computational linguistics, approaches aiming to characterize it are mainly statistical, relying on language markers. In light of this, our first contribution is a framework to evaluate the ability of language models to grasp writing style. We will have previously elaborated on text embedding models in machine learning and deep learning, at the word, document, and author levels. We will also have presented the treatment of the notion of literary style in Natural Language Processing, which forms the basis of our method. Transferring knowledge between black-box large language models and these methods derived from linguistics remains a complex task. Our second contribution aims to reconcile these approaches through a representation learning model focusing on style, VADES (Variational Author and Document Embedding with Style). We compare our model to state-of-the-art ones and analyze their limitations in this context.Finally, we delve into dynamic author and document embeddings. Temporal information is crucial, allowing for a more fine-grained representation of writing dynamics. After presenting the state of the art, we elaborate on our last contribution, B²ADE (Brownian Bridge Author and Document Embedding), which models authors as trajectories. We conclude by outlining several leads for improving our methods and highlighting potential research directions for the future
Sayadi, Karim. "Classification du texte numérique et numérisé. Approche fondée sur les algorithmes d'apprentissage automatique." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066079/document.
Different disciplines in the humanities, such as philology or palaeography, face complex and time-consuming tasks whenever it comes to examining the data sources. The introduction of computational approaches in humanities makes it possible to address issues such as semantic analysis and systematic archiving. The conceptual models developed are based on algorithms that are later hard coded in order to automate these tedious tasks. In the first part of the thesis we propose a novel method to build a semantic space based on topics modeling. In the second part and in order to classify historical documents according to their script. We propose a novel representation learning method based on stacking convolutional auto-encoder. The goal is to automatically learn plot representations of the script or the written language
Wauquier, Pauline. "Task driven representation learning." Thesis, Lille 3, 2017. http://www.theses.fr/2017LIL30005/document.
Machine learning proposes numerous algorithms to solve the different tasks that can be extracted from real world prediction problems. To solve the different concerned tasks, most Machine learning algorithms somehow rely on relationships between instances. Pairwise instances relationships can be obtained by computing a distance between the vectorial representations of the instances. Considering the available vectorial representation of the data, none of the commonly used distances is ensured to be representative of the task that aims at being solved. In this work, we investigate the gain of tuning the vectorial representation of the data to the distance to more optimally solve the task. We more particularly focus on an existing graph-based algorithm for classification task. An algorithm to learn a mapping of the data in a representation space which allows an optimal graph-based classification is first introduced. By projecting the data in a representation space in which the predefined distance is representative of the task, we aim at outperforming the initial vectorial representation of the data when solving the task. A theoretical analysis of the introduced algorithm is performed to define the conditions ensuring an optimal classification. A set of empirical experiments allows us to evaluate the gain of the introduced approach and to temper the theoretical analysis
Dos, Santos Ludovic. "Representation learning for relational data." Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066480/document.
The increasing use of social and sensor networks generates a large quantity of data that can be represented as complex graphs. There are many tasks from information analysis, to prediction and retrieval one can imagine on those data where relation between graph nodes should be informative. In this thesis, we proposed different models for three different tasks: - Graph node classification - Relational time series forecasting - Collaborative filtering. All the proposed models use the representation learning framework in its deterministic or Gaussian variant. First, we proposed two algorithms for the heterogeneous graph labeling task, one using deterministic representations and the other one Gaussian representations. Contrary to other state of the art models, our solution is able to learn edge weights when learning simultaneously the representations and the classifiers. Second, we proposed an algorithm for relational time series forecasting where the observations are not only correlated inside each series, but also across the different series. We use Gaussian representations in this contribution. This was an opportunity to see in which way using Gaussian representations instead of deterministic ones was profitable. At last, we apply the Gaussian representation learning approach to the collaborative filtering task. This is a preliminary work to see if the properties of Gaussian representations found on the two previous tasks were also verified for the ranking one. The goal of this work was to then generalize the approach to more relational data and not only bipartite graphs between users and items
Belharbi, Soufiane. "Neural networks regularization through representation learning." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMIR10/document.
Neural network models and deep models are one of the leading and state of the art models in machine learning. They have been applied in many different domains. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such models requires a large number of training samples which is not always available. One of the fundamental issues in neural networks is overfitting which is the issue tackled in this thesis. Such problem often occurs when the training of large models is performed using few training samples. Many approaches have been proposed to prevent the network from overfitting and improve its generalization performance such as data augmentation, early stopping, parameters sharing, unsupervised learning, dropout, batch normalization, etc. In this thesis, we tackle the neural network overfitting issue from a representation learning perspective by considering the situation where few training samples are available which is the case of many real world applications. We propose three contributions. The first one presented in chapter 2 is dedicated to dealing with structured output problems to perform multivariate regression when the output variable y contains structural dependencies between its components. Our proposal aims mainly at exploiting these dependencies by learning them in an unsupervised way. Validated on a facial landmark detection problem, learning the structure of the output data has shown to improve the network generalization and speedup its training. The second contribution described in chapter 3 deals with the classification task where we propose to exploit prior knowledge about the internal representation of the hidden layers in neural networks. This prior is based on the idea that samples within the same class should have the same internal representation. We formulate this prior as a penalty that we add to the training cost to be minimized. Empirical experiments over MNIST and its variants showed an improvement of the network generalization when using only few training samples. Our last contribution presented in chapter 4 showed the interest of transfer learning in applications where only few samples are available. The idea consists in re-using the filters of pre-trained convolutional networks that have been trained on large datasets such as ImageNet. Such pre-trained filters are plugged into a new convolutional network with new dense layers. Then, the whole network is trained over a new task. In this contribution, we provide an automatic system based on such learning scheme with an application to medical domain. In this application, the task consists in localizing the third lumbar vertebra in a 3D CT scan. A pre-processing of the 3D CT scan to obtain a 2D representation and a post-processing to refine the decision are included in the proposed system. This work has been done in collaboration with the clinic "Rouen Henri Becquerel Center" who provided us with data
Vukotic, Verdran. "Deep Neural Architectures for Automatic Representation Learning from Multimedia Multimodal Data." Thesis, Rennes, INSA, 2017. http://www.theses.fr/2017ISAR0015/document.
In this dissertation, the thesis that deep neural networks are suited for analysis of visual, textual and fused visual and textual content is discussed. This work evaluates the ability of deep neural networks to learn automatic multimodal representations in either unsupervised or supervised manners and brings the following main contributions:1) Recurrent neural networks for spoken language understanding (slot filling): different architectures are compared for this task with the aim of modeling both the input context and output label dependencies.2) Action prediction from single images: we propose an architecture that allow us to predict human actions from a single image. The architecture is evaluated on videos, by utilizing solely one frame as input.3) Bidirectional multimodal encoders: the main contribution of this thesis consists of neural architecture that translates from one modality to the other and conversely and offers and improved multimodal representation space where the initially disjoint representations can translated and fused. This enables for improved multimodal fusion of multiple modalities. The architecture was extensively studied an evaluated in international benchmarks within the task of video hyperlinking where it defined the state of the art today.4) Generative adversarial networks for multimodal fusion: continuing on the topic of multimodal fusion, we evaluate the possibility of using conditional generative adversarial networks to lean multimodal representations in addition to providing multimodal representations, generative adversarial networks permit to visualize the learned model directly in the image domain
Karpate, Yogesh. "Enhanced representation & learning of magnetic resonance signatures in multiple sclerosis." Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S068/document.
Multiple Sclerosis (MS) is an acquired inflammatory disease, which causes disabilities in young adults and it is common in northern hemisphere. This PhD work focuses on characterization and modeling of multidimensional MRI signatures in MS Lesions (MSL). The objective is to improve image representation and learning for visual recognition, where high level information such as MSL contained in MRI are automatically extracted. We propose a new longitudinal intensity normalization algorithm for multichannel MRI in the presence of MS lesions, which provides consistent and reliable longitudinal detections. This is primarily based on learning the tissue intensities from multichannel MRI using robust Gaussian Mixture Modeling. Further, we proposed two MSL detection methods based on a statistical patient to population comparison framework and probabilistic one class learning. We evaluated our proposed algorithms on multi-center databases to verify its efficacy
Soltan-Zadeh, Yasaman. "Improved rule-based document representation and classification using genetic programming." Thesis, Royal Holloway, University of London, 2011. http://repository.royalholloway.ac.uk/items/479a1773-779b-8b24-b334-7ed485311abe/8/.
Lu, Ying. "Transfer Learning for Image Classification." Thesis, Lyon, 2017. http://www.theses.fr/2017LYSEC045/document.
When learning a classification model for a new target domain with only a small amount of training samples, brute force application of machine learning algorithms generally leads to over-fitted classifiers with poor generalization skills. On the other hand, collecting a sufficient number of manually labeled training samples may prove very expensive. Transfer Learning methods aim to solve this kind of problems by transferring knowledge from related source domain which has much more data to help classification in the target domain. Depending on different assumptions about target domain and source domain, transfer learning can be further categorized into three categories: Inductive Transfer Learning, Transductive Transfer Learning (Domain Adaptation) and Unsupervised Transfer Learning. We focus on the first one which assumes that the target task and source task are different but related. More specifically, we assume that both target task and source task are classification tasks, while the target categories and source categories are different but related. We propose two different methods to approach this ITL problem. In the first work we propose a new discriminative transfer learning method, namely DTL, combining a series of hypotheses made by both the model learned with target training samples, and the additional models learned with source category samples. Specifically, we use the sparse reconstruction residual as a basic discriminant, and enhance its discriminative power by comparing two residuals from a positive and a negative dictionary. On this basis, we make use of similarities and dissimilarities by choosing both positively correlated and negatively correlated source categories to form additional dictionaries. A new Wilcoxon-Mann-Whitney statistic based cost function is proposed to choose the additional dictionaries with unbalanced training data. Also, two parallel boosting processes are applied to both the positive and negative data distributions to further improve classifier performance. On two different image classification databases, the proposed DTL consistently out performs other state-of-the-art transfer learning methods, while at the same time maintaining very efficient runtime. In the second work we combine the power of Optimal Transport and Deep Neural Networks to tackle the ITL problem. Specifically, we propose a novel method to jointly fine-tune a Deep Neural Network with source data and target data. By adding an Optimal Transport loss (OT loss) between source and target classifier predictions as a constraint on the source classifier, the proposed Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data. Furthermore, by using different kind of metric as cost matrix for the OT loss, JTLN can incorporate different prior knowledge about the relatedness between target categories and source categories. We carried out experiments with JTLN based on Alexnet on image classification datasets and the results verify the effectiveness of the proposed JTLN in comparison with standard consecutive fine-tuning. To the best of our knowledge, the proposed JTLN is the first work to tackle ITL with Deep Neural Networks while incorporating prior knowledge on relatedness between target and source categories. This Joint Transfer Learning with OT loss is general and can also be applied to other kind of Neural Networks
Alaverdyan, Zaruhi. "Unsupervised representation learning for anomaly detection on neuroimaging. Application to epilepsy lesion detection on brain MRI." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI005/document.
This work represents one attempt to develop a computer aided diagnosis system for epilepsy lesion detection based on neuroimaging data, in particular T1-weighted and FLAIR MR sequences. Given the complexity of the task and the lack of a representative voxel-level labeled data set, the adopted approach, first introduced in Azami et al., 2016, consists in casting the lesion detection task as a per-voxel outlier detection problem. The system is based on training a one-class SVM model for each voxel in the brain on a set of healthy controls, so as to model the normality of the voxel. The main focus of this work is to design representation learning mechanisms, capturing the most discriminant information from multimodality imaging. Manual features, designed to mimic the characteristics of certain epilepsy lesions, such as focal cortical dysplasia (FCD), on neuroimaging data, are tailored to individual pathologies and cannot discriminate a large range of epilepsy lesions. Such features reflect the known characteristics of lesion appearance; however, they might not be the most optimal ones for the task at hand. Our first contribution consists in proposing various unsupervised neural architectures as potential feature extracting mechanisms and, eventually, introducing a novel configuration of siamese networks, to be plugged into the outlier detection context. The proposed system, evaluated on a set of T1-weighted MRIs of epilepsy patients, showed a promising performance but a room for improvement as well. To this end, we considered extending the CAD system so as to accommodate multimodality data which offers complementary information on the problem at hand. Our second contribution, therefore, consists in proposing strategies to combine representations of different imaging modalities into a single framework for anomaly detection. The extended system showed a significant improvement on the task of epilepsy lesion detection on T1-weighted and FLAIR MR images. Our last contribution focuses on the integration of PET data into the system. Given the small number of available PET images, we make an attempt to synthesize PET data from the corresponding MRI acquisitions. Eventually we show an improved performance of the system when trained on the mixture of synthesized and real images
Tinas, Jean-louis. "Apprentissage d’un concept scientifique : statut de l’hypothese dans la demarche d’investigation en sciences physiques." Thesis, Bordeaux 2, 2013. http://www.theses.fr/2013BOR22051/document.
To learn a scientific concept proceeds of a process of demolition-reconstruction. To teach means helping the pupil in this approach which asks him to replay, for him the route of invention which allowed the emergence of the concept. It is exactly to face the crisis which crosses the scientific education in France and in the world and because we consider that the usual, still used educational practices, are partly responsible for it, that the approach of investigation is universally proposed. To proceed by investigation is a method which asks to the pupil to build his knowledge. She is presented as being more effective to learn. A reflection around the reason of this efficiency leads us to stop at the level of the stage of formulation of hypothesis which seems to constitute the pivot of the approach. Pupils’ statements for which we deduce that they are the translation of their representation show that it is possible to explore their state of thought in a situation of learning and better, to follow processes of thought. The methods developed for it seem effective because we succeed in showing on the scale of a class that thanks to the formulation of hypotheses all the pupils succeed, with their rhythm, in reaching the scientific knowledge. So, we notice that the hypothesis plays a role structuring for the knowledge under construction. She trains it for measure of the process of demolition-reconstruction. These considerations authorize us to think that the use of the formulation of hypothesis contributes to the efficiency of the approach by investigation compared with a more classic approach to learn a scientific knowledge
Kim, Seungyeon. "Novel document representations based on labels and sequential information." Diss., Georgia Institute of Technology, 2015. http://hdl.handle.net/1853/53946.
Jain, Himalaya. "Learning compact representations for large scale image search." Thesis, Rennes 1, 2018. http://www.theses.fr/2018REN1S027/document.
This thesis addresses the problem of large-scale image search. To tackle image search at large scale, it is required to encode images with compact representations which can be efficiently employed to compare images meaningfully. Obtaining such compact representation can be done either by compressing effective high dimensional representations or by learning compact representations in an end-to-end manner. The work in this thesis explores and advances in both of these directions. In our first contribution, we extend structured vector quantization approaches such as Product Quantization by proposing a weighted codeword sum representation. We test and verify the benefits of our approach for approximate nearest neighbor search on local and global image features which is an important way to approach large scale image search. Learning compact representation for image search recently got a lot of attention with various deep hashing based approaches being proposed. In such approaches, deep convolutional neural networks are learned to encode images into compact binary codes. In this thesis we propose a deep supervised learning approach for structured binary representation which is a reminiscent of structured vector quantization approaches such as PQ. Our approach benefits from asymmetric search over deep hashing approaches and gives a clear improvement for search accuracy at the same bit-rate. Inverted index is another important part of large scale search system apart from the compact representation. To this end, we extend our ideas for supervised compact representation learning for building inverted indexes. In this work we approach inverted indexing with supervised deep learning and make an attempt to unify the learning of inverted index and compact representation. We thoroughly evaluate all the proposed methods on various publicly available datasets. Our methods either outperform, or are competitive with the state-of-the-art
Zhang, Yuyao. "Non-linear dimensionality reduction and sparse representation models for facial analysis." Thesis, Lyon, INSA, 2014. http://www.theses.fr/2014ISAL0019/document.
Face analysis techniques commonly require a proper representation of images by means of dimensionality reduction leading to embedded manifolds, which aims at capturing relevant characteristics of the signals. In this thesis, we first provide a comprehensive survey on the state of the art of embedded manifold models. Then, we introduce a novel non-linear embedding method, the Kernel Similarity Principal Component Analysis (KS-PCA), into Active Appearance Models, in order to model face appearances under variable illumination. The proposed algorithm successfully outperforms the traditional linear PCA transform to capture the salient features generated by different illuminations, and reconstruct the illuminated faces with high accuracy. We also consider the problem of automatically classifying human face poses from face views with varying illumination, as well as occlusion and noise. Based on the sparse representation methods, we propose two dictionary-learning frameworks for this pose classification problem. The first framework is the Adaptive Sparse Representation pose Classification (ASRC). It trains the dictionary via a linear model called Incremental Principal Component Analysis (Incremental PCA), tending to decrease the intra-class redundancy which may affect the classification performance, while keeping the extra-class redundancy which is critical for sparse representation. The other proposed work is the Dictionary-Learning Sparse Representation model (DLSR) that learns the dictionary with the aim of coinciding with the classification criterion. This training goal is achieved by the K-SVD algorithm. In a series of experiments, we show the performance of the two dictionary-learning methods which are respectively based on a linear transform and a sparse representation model. Besides, we propose a novel Dictionary Learning framework for Illumination Normalization (DL-IN). DL-IN based on sparse representation in terms of coupled dictionaries. The dictionary pairs are jointly optimized from normally illuminated and irregularly illuminated face image pairs. We further utilize a Gaussian Mixture Model (GMM) to enhance the framework's capability of modeling data under complex distribution. The GMM adapt each model to a part of the samples and then fuse them together. Experimental results demonstrate the effectiveness of the sparsity as a prior for patch-based illumination normalization for face images
Cherti, Mehdi. "Deep generative neural networks for novelty generation : a foundational framework, metrics and experiments." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS029/document.
In recent years, significant advances made in deep neural networks enabled the creation of groundbreaking technologies such as self-driving cars and voice-enabled personal assistants. Almost all successes of deep neural networks are about prediction, whereas the initial breakthroughs came from generative models. Today, although we have very powerful deep generative modeling techniques, these techniques are essentially being used for prediction or for generating known objects (i.e., good quality images of known classes): any generated object that is a priori unknown is considered as a failure mode (Salimans et al., 2016) or as spurious (Bengio et al., 2013b). In other words, when prediction seems to be the only possible objective, novelty is seen as an error that researchers have been trying hard to eliminate. This thesis defends the point of view that, instead of trying to eliminate these novelties, we should study them and the generative potential of deep nets to create useful novelty, especially given the economic and societal importance of creating new objects in contemporary societies. The thesis sets out to study novelty generation in relationship with data-driven knowledge models produced by deep generative neural networks. Our first key contribution is the clarification of the importance of representations and their impact on the kind of novelties that can be generated: a key consequence is that a creative agent might need to rerepresent known objects to access various kinds of novelty. We then demonstrate that traditional objective functions of statistical learning theory, such as maximum likelihood, are not necessarily the best theoretical framework for studying novelty generation. We propose several other alternatives at the conceptual level. A second key result is the confirmation that current models, with traditional objective functions, can indeed generate unknown objects. This also shows that even though objectives like maximum likelihood are designed to eliminate novelty, practical implementations do generate novelty. Through a series of experiments, we study the behavior of these models and the novelty they generate. In particular, we propose a new task setup and metrics for selecting good generative models. Finally, the thesis concludes with a series of experiments clarifying the characteristics of models that can exhibit novelty. Experiments show that sparsity, noise level, and restricting the capacity of the net eliminates novelty and that models that are better at recognizing novelty are also good at generating novelty
Tamaazousti, Youssef. "Vers l’universalité des représentations visuelle et multimodales." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC038/document.
Because of its key societal, economic and cultural stakes, Artificial Intelligence (AI) is a hot topic. One of its main goal, is to develop systems that facilitates the daily life of humans, with applications such as household robots, industrial robots, autonomous vehicle and much more. The rise of AI is highly due to the emergence of tools based on deep neural-networks which make it possible to simultaneously learn, the representation of the data (which were traditionally hand-crafted), and the task to solve (traditionally learned with statistical models). This resulted from the conjunction of theoretical advances, the growing computational capacity as well as the availability of many annotated data. A long standing goal of AI is to design machines inspired humans, capable of perceiving the world, interacting with humans, in an evolutionary way. We categorize, in this Thesis, the works around AI, in the two following learning-approaches: (i) Specialization: learn representations from few specific tasks with the goal to be able to carry out very specific tasks (specialized in a certain field) with a very good level of performance; (ii) Universality: learn representations from several general tasks with the goal to perform as many tasks as possible in different contexts. While specialization was extensively explored by the deep-learning community, only a few implicit attempts were made towards universality. Thus, the goal of this Thesis is to explicitly address the problem of improving universality with deep-learning methods, for image and text data. We have addressed this topic of universality in two different forms: through the implementation of methods to improve universality (“universalizing methods”); and through the establishment of a protocol to quantify its universality. Concerning universalizing methods, we proposed three technical contributions: (i) in a context of large semantic representations, we proposed a method to reduce redundancy between the detectors through, an adaptive thresholding and the relations between concepts; (ii) in the context of neural-network representations, we proposed an approach that increases the number of detectors without increasing the amount of annotated data; (iii) in a context of multimodal representations, we proposed a method to preserve the semantics of unimodal representations in multimodal ones. Regarding the quantification of universality, we proposed to evaluate universalizing methods in a Transferlearning scheme. Indeed, this technical scheme is relevant to assess the universal ability of representations. This also led us to propose a new framework as well as new quantitative evaluation criteria for universalizing methods
Isaac, Yoann. "Représentations redondantes pour les signaux d’électroencéphalographie." Thesis, Paris 11, 2015. http://www.theses.fr/2015PA112072/document.
The electroencephalography measures the brain activity by recording variations of the electric field on the surface of the skull. This measurement is usefull in various applications like medical diagnosis, analysis of brain functionning or whithin brain-computer interfaces. Numerous studies have tried to develop methods for analyzing these signals in order to extract various components of interest, however, none of them allows to extract them with sufficient reliabilty. This thesis focuses on the development of approaches considering redundant (overcomoplete) representations for these signals. During the last years, these representations have been shown particularly efficient to describe various classes of signals due to their flexibility. Obtaining such representations for EEG presents some difficuties due to the low signal-to-noise ratio of these signals. We propose in this study to overcome them by guiding the methods considered to physiologically plausible representations thanks to well-suited regularizations. These regularizations are built from prior knowledge about the spatial and temporal properties of these signals. For each regularization, an algorithm is proposed to solve the optimization problem allowing to obtain the targeted representations. The evaluation of the proposed EEG signals approaches highlights their effectiveness in representing them
Mohammadi, Samin. "Analysis of user popularity pattern and engagement prediction in online social networks." Thesis, Evry, Institut national des télécommunications, 2018. http://www.theses.fr/2018TELE0019/document.
Nowadays, social media has widely affected every aspect of human life. The most significant change in people's behavior after emerging Online Social Networks (OSNs) is their communication method and its range. Having more connections on OSNs brings more attention and visibility to people, where it is called popularity on social media. Depending on the type of social network, popularity is measured by the number of followers, friends, retweets, likes, and all those other metrics that is used to calculate engagement. Studying the popularity behavior of users and published contents on social media and predicting its future status are the important research directions which benefit different applications such as recommender systems, content delivery networks, advertising campaign, election results prediction and so on. This thesis addresses the analysis of popularity behavior of OSN users and their published posts in order to first, identify the popularity trends of users and posts and second, predict their future popularity and engagement level for published posts by users. To this end, i) the popularity evolution of ONS users is studied using a dataset of 8K Facebook professional users collected by an advanced crawler. The collected dataset includes around 38 million snapshots of users' popularity values and 64 million published posts over a period of 4 years. Clustering temporal sequences of users' popularity values led to identifying different and interesting popularity evolution patterns. The identified clusters are characterized by analyzing the users' business sector, called category, their activity level, and also the effect of external events. Then ii) the thesis focuses on the prediction of user engagement on the posts published by users on OSNs. A novel prediction model is proposed which takes advantage of Point-wise Mutual Information (PMI) and predicts users' future reaction to newly published posts. Finally, iii) the proposed model is extended to get benefits of representation learning and predict users' future engagement on each other's posts. The proposed prediction approach extracts user embedding from their reaction history instead of using conventional feature extraction methods. The performance of the proposed model proves that it outperforms conventional learning methods available in the literature. The models proposed in this thesis, not only improves the reaction prediction models to exploit representation learning features instead of hand-crafted features but also could help news agencies, advertising campaigns, content providers in CDNs, and recommender systems to take advantage of more accurate prediction results in order to improve their user services
Guilment, Thomas. "Classification de vocalises de mammifères marins en environnement sismique." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2018. http://www.theses.fr/2018IMTA0080/document.
In partnership with Sercel, the thesis concerns the implementation of algorithms for recognizing the sounds emitted by mysticetes (baleen whales). These sounds can be studiedusing passive acoustic monitoring systems. Sercel, through its seismic activities related to oïl exploration, has its own software to detect and locate underwater sound energy sources. The thesis work therefore consists in adding a recognition module to identify if the detected andlocalized energy corresponds to a possible mysticete. Since seismic shooting campaigns areexpensive, the method used must be able to reduce the probability of false alarms, as recognitioncan invalidate detection. The proposed method is based on dictionary learning. It is dynamic, modular, depends on few parameters and is robust to false alarms. An experiment on five types of vocalizations is presented. We obtain an average recall of 92.1% while rejecting 97.3% of the noises (persistent and transient). In addition, a confidence coefficient is associated with each recognition and allows semi-supervised incremental learning to be achieved. Finally, we propose a method capable of managing detection and recognition together. This "multiclassdetector" best respects the constraints of false alarm management and allows several types of vocalizations to be identified at the same time. This method is well adapted to the industrial context for which it is dedicated. It also opens up very promising prospects in the bioacoustic context
Dupuy, Eric. "Construction d’une notion scientifique et invariant : le cas d'élèves de l'enseignement primaire." Thesis, Bordeaux 2, 2009. http://www.theses.fr/2009BOR21652/document.
The purpose of this dissertation is to study how scientific conceptions are constructed in the course of experimental activities in physical sciences by young children at school. The study is based on three principal hypotheses: a) The formation of concepts and notions depends on invariant elements. b) The elaboration of thought results from personal reflections, actions and exchanges all anchored in a social dynamic process. c) Representations reveal and organise modes of thinking and their actualisation. In the first stage, the dissertation focuses on the formation of the notion of concept: from the evidencing of invariants to a stable conceptual architecture. Next, it presents the questions raised by the notion of learning and the expected achievement of the learner’s autonomy. Then, it develops a theory of representation, considering the question of the constitution and realisation of knowledge. In a second stage, the dissertation conducts its experimentations within the framework of an observation of classroom situations, the conversion of concrete situations into interpretable data being based on the phenomenological hypothesis from the point of view of constructivist epistemology. One situation refers to the theme of shade, the other to that of electricity: both evidence a complex process of cognitive elaboration, giving rise to conceptions based on a set of invariants. The representations thus reveal and structure the processes of thought. While « childish » items (R1) prove to be numerous, there also often emerge « rationalising » items (R2), either image-based or resting on internal dynamics. Finally, the dissertation demonstrates, in a still empirical way, how certain item combinations evince, so to speak before our very eyes, the child’s process of thinking in action — i.e. « enaction » in the Varela sense of the word
Diese Arbeit befasst sich mit der Konstruktion von wissenschaftlichen Konzepten im Verlauf von physikalischen Experimenten ,die Schüler im Unterricht durchführen. Sie stützt sich dabei auf drei Hypothesen. Die Bildung von Konzepten und Begriffen strukturiert sich um Invarianten. Die Erarbeitung eines Gedankens ergibt sich aus der Verbindung von eigenständigen Überlegungen, von Handlungen und von in sozialer Dynamik verankertem Austausch. Repräsentationen zeigen Modalitäten des Denkens und ihre Aktualisierung auf und organisieren sie. Diese Arbeit fokalisiert sich zunächst auf die Ausbildung des Konzeptbegriffs: vom Erfassen von Invarianten hin zu einer stabilen Konzeptarchitektur. Dann geht sie auf die Fragestellungen des Lernbegriffs ein und auf die Perspektive der Autonomie des Lernenden. Schließlich stellt sie die Repräsentationstheorie dar und fragt nach der Ausformung und der Offenkundigkeit der Erkenntnis. Im zweiten Teil dieser Arbeit werden die Experimente in Form von Beobachtungen in der Schule ausgewertet. Dabei beruht die Umwandlung von erlebten Situationen in verwertbare Daten auf der phänomenologischen Hypothese einer konstruktivistischen Epistemologie. Ein Experiment beschäftigt sich mit dem Schatten, das andere mit dem Thema Elektrizität. Sie belegen eine komplexe kognitive Erarbeitung, die zu Konzepten auf der Grundlage von Invarianten führen. Durch Repräsentationen werden die Gedankengänge offensichtlich und strukturiert. Auch wenn es zahlreich „kindliche“ Item (R1) gibt, werden „rationalisierende“ Item (von R2) oft mit Hilfe einer „bildgebenden“ Repräsentation (R1?R2) oder einer internen Dynamik (R2?R2) freigesetzt. Auf noch empirische Weise zeigt diese Arbeit schließlich wie gewisse Kombinationen von Item sozusagen unter unseren Augen die Entstehung des Gedanken beim Schüler aufzeigen: eine Enaction im Sinne von Varela
Esta tesis centra su objeto en el campo de la construcción de concepciones científicas en el curso de actividades experimentales en ciencias físicas conducidas en medio escolar por alumnos. Se apoya sobre tres hipótesis mayores. La formación de los conceptos y de nociones se estructura alrededor de elementos invariantes. La elaboración del pensamiento resulta de la conjunción de reflexiones, propias acciones e intercambios anclados en una dinámica social. Las representaciones descubren y organizan las modalidades de pensamiento y su actualización. En un primer tiempo la tesis se concentra en la formación de la noción de concepto: del reconocimiento de invariantes hacia una arquitectura conceptual estable. Luego expone las preguntas que plantea la noción de aprendizaje y la perspectiva de autonomía del novato. Luego presenta la teoría de la representación y plantea la cuestión de la constitución y la puesta en evidencia del conocimiento. En un segundo tiempo, la tesis inscribe sus experimentaciones en la observación de situaciones escolares basada la hipótesis fenomenológica en una epistemológica constructivista, la condición de la transformación de situaciones vividas en datos explotables. Una sobre el tema de la sombra, otra en lo de la electricidad, dan testimonio de una elaboración cognitiva compleja de donde nacen concepciones sobre la base de invariantes, las representaciones permiten descubrir y estructurar aproches de pensamiento. Si los “ítem” infantiles (R1) son numerosos, unos “ítem” “ racionalizantes (de R2) se desprenden a menudo llevados por una representación llena de imágenes (R1?R2), o en una dinámica interne (R2?R2). Por fin, la tesis muestra, de manera aun empÍrica, cómo ciertas combinaciones de ítem manifiestan, dicho sea asÍ “bajo nuestros ojos”, el pensamiento del alumno elaborándose: una “enacción” en el sentido de Varela
Brun, Gilles. "Changement organisationnel et relation de pouvoir : Pour une approche sociocognitive du dialogue social dans l’entreprise." Thesis, Pau, 2012. http://www.theses.fr/2012PAUU2014/document.
This thesis relies heavily on the concept of "normative transformation of both innermost and social being ", transformations induced by changes in the economic and social environment to an exacerbation of individualism on the one hand referring to executives social and ideological and partly to the psyche of individuals often challenged by the turmoil transformational. Faced with this rapidly changing environment, this thesis describes, from a business case, the use of "marketing war" in the social sphere and considers the fragility and managing the optimal pace of learning the dynamics of a process of change. From the study of this research-action is deduced the potential importance of social cognitive mediation. An attempt to model the results concerning the interplay of interactions and feedbacks on multiple pathways of the future of individual freedom generated by the difficult process of subjectivation is added. The necessary development of sociocognitive mediation intra-company or inter-company is required to solve (purge) interpersonal conflicts and deploy otherness
Bourigault, Simon. "Apprentissage de représentations pour la prédiction de propagation d'information dans les réseaux sociaux." Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066368/document.
In this thesis, we study information diffusion in online social networks. Websites like Facebook or Twitter have indeed become information medias, on which users create and share a lot of data. Most existing models of the information diffusion phenomenon relies on strong hypothesis about the structure and dynamics of diffusion. In this document, we study the problem of diffusion prediction in the context where the social graph is unknown and only user actions are observed. - We propose a learning algorithm for the independant cascades model that does not take time into account. Experimental results show that this approach obtains better results than time-based learning schemes. - We then propose several representations learning methods for this task of diffusion prediction. This let us define more compact and faster models. - Finally, we apply our representation learning approach to the source detection task, where it obtains much better results than graph-based approaches
Flocon-Cholet, Joachim. "Classification audio sous contrainte de faible latence." Thesis, Rennes 1, 2016. http://www.theses.fr/2016REN1S030/document.
This thesis focuses on audio classification under low-latency constraints. Audio classification has been widely studied for the past few years, however, a large majority of the existing work presents classification systems that are not subject to temporal constraints : the audio signal can be scanned freely in order to gather the needed information to perform the decision (in that case, we may refer to an offline classification). Here, we consider audio classification in the telecommunication domain. The working conditions are now more severe : algorithms work in real time and the analysis and processing steps are now operated on the fly, as long as the signal is transmitted. Hence, the audio classification step has to meet the real time constraints, which can modify its behaviour in different ways : only the current and the past observations of the signal are available, and, despite this fact the classification system has to remain reliable and reactive. Thus, the first question that occurs is : what strategy for the classification can we adopt in order to tackle the real time constraints ? In the literature, we can find two main approaches : the frame-level classification and the segment-level classification. In the frame-level classification, the decision is performed using only the information extracted from the current audio frame. In the segment-level classification, we exploit a short-term information using data computed from the current and few past frames. The data fusion here is obtained using the process of temporal feature integration which consists of deriving relevant information based on the temporal evolution of the audio features. Based on that, there are several questions that need to be answered. What are the limits of these two classification framework ? Can an frame-level classification and a segment-level be used efficiently for any classification task ? Is it possible to obtain good performance with these approaches ? Which classification framework may lead to the best trade-off between accuracy and reactivity ? Furthermore, for the segment-level classification framework, the temporal feature integration process is mainly based on statistical models, but would it be possible to propose other methods ? Throughout this thesis, we investigate this subject by working on several concrete case studies. First, we contribute to the development of a novel audio algorithm dedicated to audio protection. The purpose of this algorithm is to detect and suppress very quickly potentially dangerous sounds for the listener. Our method, which relies on the proposition of three features, shows high detection rate and low false alarm rate in many use cases. Then, we focus on the temporal feature integration in a low-latency framework. To that end, we propose and evaluate several methodologies for the use temporal integration that lead to a good compromise between performance and reactivity. Finally, we propose a novel approach that exploits the temporal evolution of the features. This approach is based on the use of symbolic representation that can capture the temporal structure of the features. The idea is thus to find temporal patterns that are specific to each audio classes. The experiments performed with this approach show promising results
Romero-Pinazo, Sophie. "Autorégulation et représentations sociales dans les processus d'apprentissage de professionnels de l'éducation : recherches expérimentales sur les effets d’une formation par alternance dans les réseaux d’éducation prioritaire." Thesis, Aix-Marseille, 2016. http://www.theses.fr/2016AIXM3055/document.
This thesis falls within the complex system of the work/study training program of adults with an introduction to self-regulation. Which elements would participate to the changes initiated by the law of Reorganization to compensate the existing educational inequalities? Our subject is set outside school in the high-priority education network, within a plan of educational support for seven-year-olds with learning difficulties : the Reading Writing Mathematics Club. Though several studies take interest in the impact of various factors on the children’s success, little research has been done to validate the models of formative evaluation. We propose to improve the training of the Club’s staff members with an introduction to self-regulation, to stimulate the cognitive development and independence of both adults and children. Our methodology aimed to test a cause and effect relation between the staff's training and the children’s progress in both school subjects and behaviour. Our method was almost experimental, comparative, prospective, practically double blinded. Two staff groups were randomly formed. We observed how the representations they had of their own mission evolved, before and after their training; the obtained results were corroborated by the children’s results. We observed statistically significant differences which allow us to affirm that the training in self-regulation of the staff members changed their representations and led to better results for the children
Kahindo, Senge Muvingi Christian. "Analyse automatique de l’écriture manuscrite sur tablette pour la détection et le suivi thérapeutique de personnes présentant des pathologies." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLL016/document.
We present, in this thesis, a novel paradigm for assessing Alzheimer’s disease by analyzing impairment of handwriting (HW) on tablets, a challenging problem that is still in its infancy. The state of the art is dominated by methods that assume a unique behavioral trend for each cognitive profile, and that extract global kinematic parameters, assessed by standard statistical tests or classification models, for discriminating the neuropathological disorders (Alzheimer’s (AD), Mild Cognitive Impairment (MCI)) from Healthy Controls (HC). Our work tackles these two major limitations as follows. First, instead of considering a unique behavioral pattern for each cognitive profile, we relax this heavy constraint by allowing the emergence of multimodal behavioral patterns. We achieve this by performing semi-supervised learning to uncover homogeneous clusters of subjects, and then we analyze how much information these clusters carry on the cognitive profiles. Second, instead of relying on global kinematic parameters, mostly consisting of their average, we refine the encoding either by a semi-global parameterization, or by modeling the full dynamics of each parameter, harnessing thereby the rich temporal information inherently characterizing online HW. Thanks to our modeling, we obtain new findings that are the first of their kind on this research field. A striking finding is revealed: two major clusters are unveiled, one dominated by HC and MCI subjects, and one by MCI and ES-AD, thus revealing that MCI patients have fine motor skills leaning towards either HC’s or ES-AD’s. This thesis introduces also a new finding from HW trajectories that uncovers a rich set of features simultaneously like the full velocity profile, size and slant, fluidity, and shakiness, and reveals, in a naturally explainable way, how these HW features conjointly characterize, with fine and subtle details, the cognitive profiles
Piette, Eric. "Une nouvelle approche au General Game Playing dirigée par les contraintes." Thesis, Artois, 2016. http://www.theses.fr/2016ARTO0401/document.
The ability for a computer program to effectively play any strategic game, often referred to General Game Playing (GGP), is a key challenge in AI. The GGP competitions, where any game is represented according to a set of logical rules in the Game Description Language (GDL), have led researches to compare various approaches, including Monte Carlo methods, automatic constructions of evaluation functions, logic programming, and answer set programming through some general game players. In this thesis, we offer a new approach driven by stochastic constraints. We first focus on a translation process from GDL to stochastic constraint networks (SCSP) in order to provide compact representations of strategic games and to model strategies. In a second part, we exploit a fragment of SCSP through an algorithm called MAC-UCB by coupling the MAC (Maintaining Arc Consistency) algorithm, used to solve each stage of the SCSP in turn, together with the UCB (Upper Confidence Bound) policy for approximating the values of those strategies obtained by the last stage in the sequence. The efficiency of this technical on the others GGP approaches is confirmed by WoodStock, implementing MAC-UCB, the actual leader on the GGP Continuous Tournament. Finally, in the last part, we propose an alternative approach to symmetry detection in stochastic games, inspired from constraint programming techniques. We demonstrate experimentally that MAC-UCB, coupled with our constranit-based symmetry detection approach, significantly outperforms the best approaches and made WoodStock the GGP champion 2016
Aghaei, Mazaheri Jérémy. "Représentations parcimonieuses et apprentissage de dictionnaires pour la compression et la classification d'images satellites." Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S028/document.
This thesis explores sparse representation and dictionary learning methods to compress and classify satellite images. Sparse representations consist in approximating a signal by a linear combination of a few columns, known as atoms, from a dictionary, and thus representing it by only a few non-zero coefficients contained in a sparse vector. In order to improve the quality of the representations and to increase their sparsity, it is interesting to learn the dictionary. The first part of the thesis presents a state of the art about sparse representations and dictionary learning methods. Several applications of these methods are explored. Some image compression standards are also presented. The second part deals with the learning of dictionaries structured in several levels, from a tree structure to an adaptive structure, and their application to the compression of satellite images, by integrating them in an adapted coding scheme. Finally, the third part is about the use of learned structured dictionaries for the classification of satellite images. A method to estimate the Modulation Transfer Function (MTF) of the instrument used to capture an image is studied. A supervised classification algorithm, using structured dictionaries made discriminant between classes during the learning, is then presented in the scope of scene recognition in a picture
Adam, Chloé. "Pattern Recognition in the Usage Sequences of Medical Apps." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLC027/document.
Radiologists use medical imaging solutions on a daily basis for diagnosis. Improving user experience is a major line of the continuous effort to enhance the global quality and usability of software products. Monitoring applications enable to record the evolution of various software and system parameters during their use and in particular the successive actions performed by the users in the software interface. These interactions may be represented as sequences of actions. Based on this data, this work deals with two industrial topics: software crashes and software usability. Both topics imply on one hand understanding the patterns of use, and on the other developing prediction tools either to anticipate crashes or to dynamically adapt software interface according to users' needs. First, we aim at identifying crash root causes. It is essential in order to fix the original defects. For this purpose, we propose to use a binomial test to determine which type of patterns is the most appropriate to represent crash signatures. The improvement of software usability through customization and adaptation of systems to each user's specific needs requires a very good knowledge of how users use the software. In order to highlight the trends of use, we propose to group similar sessions into clusters. We compare 3 session representations as inputs of different clustering algorithms. The second contribution of our thesis concerns the dynamical monitoring of software use. We propose two methods -- based on different representations of input actions -- to address two distinct industrial issues: next action prediction and software crash risk detection. Both methodologies take advantage of the recurrent structure of LSTM neural networks to capture dependencies among our sequential data as well as their capacity to potentially handle different types of input representations for the same data
Hernandez, Sierra Gabriel. "Métodos de representación y verificación del locutor con independencia del texto." Thesis, Avignon, 2014. http://www.theses.fr/2014AVIG0203/document.
Text-independent automatic speaker recognition is a recent method in biometric area. Its increasing interest is reflected both in the increasing participation in international competitions and in the performance progresses. Moreover, the accuracy of the methods is still limited by the quantity of speaker discriminant information contained in the representations of speech utterances. This thesis presents a study on speech representation for speaker recognition systems. It shows firstly two main weaknesses. First, it fails to take into account the temporal behavior of the voice, which is known to contain speaker discriminant information. Secondly, speech events rare in a large population of speakers although very present for a given speaker are hardly taken into account by these approaches, which is contradictory when the goal is to discriminate among speakers.In order to overpass these limitations, we propose in this thesis a new speech representation for speaker recognition. This method represents each acoustic vector in a a binary space which is intrinsically speaker discriminant. A similarity measure associated with a global representation (cumulative vectors) is also proposed. This new speech utterance representation is able to represent infrequent but discriminant events and to work on temporal information. It allows also to take advantage of existing « session » variability compensation approaches (« session » variability represents all the negative variability factors). In this area, we proposed also several improvements to the usual session compensation algorithms. An original solution to deal with the temporal information inside the binary speech representation was also proposed. Thanks to a linear fusion approach between the two sources of information, we demonstrated the complementary nature of the temporal information versus the classical time independent representations
El reconocimiento automático del locutor independiente del texto, es un método dereciente incorporación en los sistemas biométricos. El desarrollo y auge del mismo serefleja en las competencias internacionales, pero aun la eficacia de los métodos de reconocimientose encuentra afectada por la cantidad de información discriminatoria dellocutor que esta presente en las representaciones actuales de las expresiones de voz.En esta tesis se realizó un estudio donde se identificaron dos principales debilidadespresentes en las representaciones actuales del locutor. En primer lugar, no se tiene encuenta el comportamiento temporal de la voz, siendo este un rasgo discriminatorio dellocutor y en segundo lugar los eventos pocos frecuentes dentro de una población delocutores pero frecuentes en un locutor dado, apenas son tenidos en cuenta por estosenfoques, lo cual es contradictorio cuando el objetivo es discriminar los locutores. Motivadopor la solución de estos problemas, se confirmó la redundancia de informaciónexistente en las representaciones actuales y la necesidad de emplear nuevas representacionesde las expresiones de voz. Se propuso un nuevo enfoque con el desarrollo de unmétodo para la obtención de un modelo generador capaz de transformar la representación actual del espacio acústico a una representación en un espacio binario, dondese propuso una medida de similitud asociada con una representación global (vectoracumulativo) que contiene tanto los eventos frecuentes como los pocos frecuentes enuna expresión de voz. Para la compensación de la variabilidad de sesión se incorporóen la matriz de dispersión intra-clase, la información común de la población de locutores,lo que implicó la modificación de tres algoritmos de la literatura que mejoraronsu desempeño respecto a la eficacia en el reconocimiento del locutor, tanto utilizandoel nuevo enfoque propuesto como el enfoque actual de referencia. La información temporalexistente en las expresiones de voz fue capturada e incorporada en una nuevarepresentación, mejorando aun más la eficacia del enfoque propuesto. Finalmente sepropuso y evaluó una fusión lineal entre los dos enfoques que demostró la informacióncomplementaria existente entre ellos, obteniéndose los mejores resultados de eficaciaen el reconocimiento del locutor
Magnan, Jean-Christophe. "Représentations graphiques de fonctions et processus décisionnels Markoviens factorisés." Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066042/document.
In decision theoretic planning, the factored framework (Factored Markovian Decision Process, FMDP) has produced several efficient algorithms in order to resolve large sequential decision making under uncertainty problems. The efficiency of this algorithms relies on data structures such as decision trees or algebraïc decision diagrams (ADDs). These planification technics are exploited in Reinforcement Learning by the architecture SDyna in order to resolve large and unknown problems. However, state-of-the-art learning and planning algorithms used in SDyna require the problem to be specified uniquely using binary variables and/or to use improvable data structure in term of compactness. In this book, we present our research works that seek to elaborate and to use a new data structure more efficient and less restrictive, and to integrate it in a new instance of the SDyna architecture. In a first part, we present the state-of-the-art modeling tools used in the algorithms that tackle large sequential decision making under uncertainty problems. We detail the modeling using decision trees and ADDs. Then we introduce the Ordered and Reduced Graphical Representation of Function, a new data structure that we propose in this thesis to deal with the various problems concerning the ADDs. We demonstrate that ORGRFs improve on ADDs to model large problems. In a second part, we go over the resolution of large sequential decision under uncertainty problems using Dynamic Programming. After the introduction of the main algorithms, we see in details the factored alternative. We indicate the improvable points of these factored versions. We describe our new algorithm that improve on these points and exploit the ORGRFs previously introduced. In a last part, we speak about the use of FMDPs in Reinforcement Learning. Then we introduce a new algorithm to learn the new datastrcture we propose. Thanks to this new algorithm, a new instance of the SDyna architecture is proposed, based on the ORGRFs : the SPIMDDI instance. We test its efficiency on several standard problems from the litterature. Finally, we present some works around this new instance. We detail a new algorithm for efficient exploration-exploitation compromise management, aiming to simplify F-RMax. Then we speak about an application of SPIMDDI to the managements of units in a strategic real time video game
Bunlon, Frédérique. "Influence de l'expérience sensorimotrice sur la perception et représentation des actions d'autrui." Thesis, Poitiers, 2015. http://www.theses.fr/2015POIT5005/document.
The aim of present work was to better understand the mechanisms by which we represent our own actions and those of others. Within the frame of the ideomotor theory, we first examined these questions in relation to imitation. Our results indicated an effect of ideomotor learning on intentional imitation (Study 1), confirming the flexibility of perception-action links, and demonstrating the role of action-effect associations in imitation. However, automatic imitation was not influenced by this type of learning (Study 2), which may suggest different processes with less sensitivity to learning ideomotor learning. We then extended our research to joint-action tasks (Study 3). We showed that an ideomotor experience, where action execution triggered actions of a non-human agent, induced a subsequent co-representation of this agent's actions (as indexed by social Simon effect). Ideomotor experience therefore seems to influence also the way we represent the actions of others in task-sharing. This work confirms the ideomotor approach to perception and representation of others' actions
Mantilla, Jauregui Juan José. "Caractérisation de pathologies cardiaques en Imagerie par Résonance Magnétique par approches parcimonieuses." Thesis, Rennes 1, 2015. http://www.theses.fr/2015REN1S073/document.
This work concerns the use of sparse representation and Dictionary Learning (DL) in order to get insights about the diseased heart in the context of Cardiovascular Diseases (CVDs). Specifically, this work focuses on 1) assessment of Left Ventricle (LV) wall motion in patients with heart failure and 2) fibrosis detection in patients with hypertrophic cardiomyopathy (HCM). In the context of heart failure (HF) patients, the work focuses on LV wall motion analysis in cardiac cine-MRI. The first contribution in this topic is a feature extraction method that exploits the partial information obtained from all temporal cardiac phases and anatomical segments in a spatio-temporal representation from sequences cine-MRI in short-axis view. These features correspond to spatio-temporal profiles in different anatomical segments of the LV. The proposed representations exploit information of the LV wall motion without segmentation needs. Three representations are proposed : 1) diametrical spatio-temporal profiles where radial motions of LV’s walls are observed at the same time in opposite anatomical segments 2) radial spatiotemporal profiles where motion of LV’s walls is observed for each segment of the LV cavity and 3) quantitative parameters extracted from the radial spatio-temporal profiles. A second contribution involves the use of these features as input atoms in the training of discriminative dictionaries to classify normal or abnormal regional LV motion. We propose two levels of evaluation, a first one where the global status of the subject (normal/pathologic) is used as ground truth to label the proposed spatio-temporal representations, and a second one where local strain information obtained from 2D Speckle Tracking Echocardiography (STE), is taken as ground truth to label the proposed features, where a profile is classified as normal or abnormal (akinetic or hypokinetic cases). In the context of Hypertrophic cardiomyopathy (HCM), we address the problem of fibrosis detection in Late Gadolinium Enhanced LGE-Short axis (SAX) images by using a sparse-based clustering approach and DL. In this framework, random image patches are taken as input atoms in order to train a classifier based on the sparse coefficients obtained with a DL approach based on kernels. For a new test LG-SAX image, the label of each pixel is predicted by using the trained classifier allowing the detection of fibrosis. A subsequent postprocessing step allows the spatial localization of fibrosis that is represented according to the American Heart Association (AHA) 17-segment model and a quantification of fibrosis in the LV myocardium
Caillat, Isabelle. "Développement d'outils de management et actes de langage dans les entreprises de spectacle vivant." Thesis, Lyon 3, 2011. http://www.theses.fr/2011LYO30052/document.
Performing arts companies operate in a context of declining resources and changes in the rules governing the allocation of grants, in accordance with the LOLF (Organic Law relative to the Laws of Finance). Their challenge lies in finding ways to address these constraints. We aim to demonstrate that their development depends on improving the manner in which all parties cooperate, based on the artistic project and taking into account the constraints resulting from the evaluation used by the LOLF, to reveal hidden costs and to develop internal resources. This research is based on the hypothesis that improving the overall performance of organizations depends on a transformative action that operates in three interdependent areas: intervention, management tools, and the speech-Actor. Based on intervention-Research in one theatre and on a qualitative study in another, we have assisted actors in the process of change management and examined the conditions in which managerial development takes place in this type of organization. We analyse how language use in the context of Socio-Economic Intervention modifies the representations and contributes to the elaboration of a new managerial instrument. We propose the use of socio-Economic management tools, serving as a framework for analyzing the organisation, combined with the criteria of evaluation and allocation of public funding as a basis of reflexion on the process of creation and dissemination of shows, as well as a means of building a shared representation between the different actors
Shih, Kai-Wun, and 施凱文. "A Study on Representation Learning Techniques for Extractive Spoken Document Summarization." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/69652994653010816915.
國立臺灣師範大學
資訊工程學系
103
The rapidly increasing availability of multimedia associated spoken documents on the Internet has prompted automatic spoken document summarization to be an important research subject. Thus far, the majority of existing work has focused on extractive spoken document summarization, which selects salient sentences from an original spoken document according to a target summarization ratio and concatenates them to form a summary concisely, in order to convey the most important theme of the document. On the other hand, there has been a surge of interest in developing representation learning techniques for a wide variety of natural language processing (NLP)-related tasks. However, to our knowledge, they are largely unexplored in the context of extractive spoken document summarization. With the above background, this thesis explores a novel use of both word and sentence representation techniques for extractive spoken document summarization. In addition, three variants of sentence ranking models built on top of such representation techniques are proposed. Furthermore, extra information cues like the prosodic features extracted from spoken documents, apart from the lexical features, are also employed for boosting the summarization performance. A series of experiments conducted on the MATBN broadcast news corpus indeed reveal the performance merits of our proposed summarization methods in relation to several state-of-the-art baselines.
Chiang, Tung-Chun, and 江東峻. "Learning Bag-of-words Document Representation with Multi-queries Memory Networks." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/45k369.
國立臺灣大學
資訊工程學研究所
106
Document representation provide essential statistical information compressed features for many tasks in the text domain, e.g., web search, question answering, document similarity and relevance judgement. Current methods use term frequencies as local features and rely on word embeddings to measure the global importance. However, the importance of words in a document might depend on the meaning of the document and can not globally measured. In this work, we propose an attention-based unsupervised predictive model to reweight the importance of words in a document. Also, considering the multiple interpretations of a single document, we multi-queries memory networks to extract the semantics in different views. And we use recurrent and gating method to combine the semantics. The experimental results show our proposed model outperforms the state-of-the-art works on two benchmark datasets.
Fu, Hao-Ming, and 傅浩明. "Learning Unsupervised Semantic Document Representation for Fine-grained Aspect-based Sentiment Analysis." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/gk32tv.
國立臺灣大學
資訊工程學研究所
107
Document representation is the core of many NLP tasks on machine understanding. A general representation learned in an unsupervised manner reserves generality and can be used for various applications. In practice, sentiment analysis (SA) has been a challenging task that is regarded to be deeply semantic-related and is often used to assess general representations. Existing methods on unsupervised document representation learning can be separated into two families: sequential ones, which explicitly take the ordering of words into consideration, and non-sequential ones, which do not explicitly do so. However, both of them suffer from their own weaknesses. In this paper, we propose a model that overcomes difficulties encountered by both families of methods. Experiments show that our model outperforms state-of-the-art methods on popular SA datasets and a fine-grained aspect-based SA by a large margin.
Ouzir, Nora. "Cardiac motion estimation in ultrasound images using a sparse representation and dictionary learning." Thesis, 2018. http://www.theses.fr/2018TOU30149/document.
Cardiovascular diseases have become a major healthcare issue. Improving the diagnosis and analysis of these diseases have thus become a primary concern in cardiology. The heart is a moving organ that undergoes complex deformations. Therefore, the quantification of cardiac motion from medical images, particularly ultrasound, is a key part of the techniques used for diagnosis in clinical practice. Thus, significant research efforts have been directed toward developing new cardiac motion estimation methods. These methods aim at improving the quality and accuracy of the estimated motions. However, they are still facing many challenges due to the complexity of cardiac motion and the quality of ultrasound images. Recently, learning-based techniques have received a growing interest in the field of image processing. More specifically, sparse representations and dictionary learning strategies have shown their efficiency in regularizing different ill-posed inverse problems. This thesis investigates the benefits that such sparsity and learning-based techniques can bring to cardiac motion estimation. Three main contributions are presented, investigating different aspects and challenges that arise in echocardiography. Firstly, a method for cardiac motion estimation using a sparsity-based regularization is introduced. The motion estimation problem is formulated as an energy minimization, whose data fidelity term is built using the assumption that the images are corrupted by multiplicative Rayleigh noise. In addition to a classical spatial smoothness constraint, the proposed method exploits the sparse properties of the cardiac motion to regularize the solution via an appropriate dictionary learning step. Secondly, a fully robust optical flow method is proposed. The aim of this work is to take into account the limitations of ultrasound imaging and the violations of the regularization constraints. In this work, two regularization terms imposing spatial smoothness and sparsity of the motion field in an appropriate cardiac motion dictionary are also exploited. In order to ensure robustness to outliers, an iteratively re-weighted minimization strategy is proposed using weighting functions based on M-estimators. As a last contribution, we investigate a cardiac motion estimation method using a combination of sparse, spatial and temporal regularizations. The problem is formulated within a general optical flow framework. The proposed temporal regularization enforces smoothness of the motion trajectories between consecutive images. Furthermore, an iterative groupewise motion estimation allows us to incorporate the three regularization terms, while enabling the processing of the image sequence as a whole. Throughout this thesis, the proposed contributions are validated using synthetic and realistic simulated cardiac ultrasound images. These datasets with available groundtruth are used to evaluate the accuracy of the proposed approaches and show their competitiveness with state-of-the-art algorithms. In order to demonstrate clinical feasibility, in vivo sequences of healthy and pathological subjects are considered for the first two methods. A preliminary investigation is conducted for the last contribution, i.e., exploiting temporal smoothness, using simulated data
Ciftci, Tolga. "A Framework for Re-Purposing Textbooks Using Learning Outcomes/Methodology, Device Characteristics, Representation and User Dimensions." Thesis, 2013. http://hdl.handle.net/1969.1/149517.