1,721,088 research outputs found
Staged Reinforcement Learning for Complex Tasks Through Decomposed Environments
No full textReinforcement Learning (RL) is an area of growing interest in the field of artificial intelligence due to its many notable applications in diverse fields. Particularly within the context of intelligent vehicle control, RL has made impressive progress. However, currently it is still in simulated controlled environments where RL can achieve its full super-human potential. Although how to apply simulation experience in real scenarios has been studied, how to approximate simulated problems to the real dynamic problems is still a challenge. In this paper, we discuss two methods that approximate RL problems to real problems. In the context of traffic junction simulations, we demonstrate that, if we can decompose a complex task into multiple sub-tasks, solving these tasks first can be advantageous to help minimising possible occurrences of catastrophic events in the complex task. From a multi-agent perspective, we introduce a training structuring mechanism that exploits the use of experience learned under the popular paradigm called Centralised Training Decentralised Execution (CTDE). This experience can then be leveraged in fully decentralised settings that are conceptually closer to real settings, where agents often do not have access to a central oracle and must be treated as isolated independent units. The results show that the proposed approaches improve agents performance in complex tasks related to traffic junctions, minimizing potential safety-critical problems that might happen in these scenarios. Although still in simulation, the investigated situations are conceptually closer to real scenarios and thus, with these results, we intend to motivate further research in the subject
Processing of longitudinal series for medical imaging
No full textL'imagerie médicale ne cesse de profiter des progrès technologiques et scientifiques. Elle permet d’explorer le corps humain sans examens intrusifs et d'opérer avec grande précision. La mise en avant des innovations technologies durant ces dernières années a favorisé l’émergence de nouvelles techniques pour l’aide au diagnostic. Pour des fins de précisions, le diagnostic peut être réalisé aujourd’hui sur des séries longitudinales d’images. Durant ces années de thèse, trois contributions ont été proposées : Nous avons présenté une méthode de pronostic Covid-19 basée sur des architectures d'apprentissage en profondeur. La méthode proposée est basée sur la combinaison d'un réseau de neurones convolutifs et récurrents pour classifier des images radiographiques thoraciques multi-temporelles et prédire l'évolution de la pathologie pulmonaire observée. L’un des principaux défis dans les méthodes d’apprentissage est l’optimisation des poids du réseau. Dans ce contexte, nous avons développé une nouvelle méthode d'optimisation bayésienne permettant d'ajuster les poids des réseaux de neurones artificiels parcimonieux. La méthode proposée repose sur la dynamique hamiltonienne avec des régularisations non lisses. Par la suite, nous étendons dans la troisième contribution le schéma d’optimisation en proposant une fonction d’activation entraînable à l’aide des Chaîne de Markov Monte Carlo.Medical imaging continues to benefit from technological and scientific progress. It allows to explore the human body without intrusive examinations and to operate with high precision. The highlighting of technological innovations in recent years has favored the emergence of new techniques for diagnostic assistance. To be more precise, a diagnosis can be made today on longitudinal series of images. During these years of the thesis, three contributions have been proposed: We have proposed a Covid-19 prognosis method based on deep learning architectures. The proposed method is based on the combination of a convolutional and recurrent neural network to classify multi-temporal chest X-ray images and predict the evolution of the observed lung pathology. One of the main challenges in learning methods is the optimization of network weights. In this context, we have developed a new Bayesian optimization method to adjust the weights of sparse artificial neural networks. The proposed method is based on Hamiltonian dynamics with non-smooth regularizations. Then, in the third contribution, we extend the optimization scheme by proposing a trainable activation function using Markov Monte Carlo chains
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
A Bayesian grouplet transform
Full text linkIn the signal processing literature, wavelet transforms have been widely used for compression, restoration or texture processing. In this sense, grouplet transforms have been proposed to account for the geometrical image regularities. A grouplet transform (basis or frame) is based on an a priori fixed association field that groups image coefficients according to geometrical considerations. In this paper, we propose a method for estimating this association field in a Bayesian way. The resulting association field is therefore adaptive to the processed image content. A hierarchical Bayesian model is proposed and the inference is conducted using a Markov Chain Monte Carlo (MCMC) algorithm. The proposed method is tested on standard images in terms of association field quality and quantitative properties of the obtained wavelet coefficients. Specifically, the proposed method provides coefficients with low correlation level, and for which the highest level of energy is concentrated within the 20% most significant. These promising results confirm the potential of the proposed method for several image processing applications such as compression, denoising or restoration
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Digital health approach for predictive, preventive, personalised and participatory medicine
No full textProblèmes de reconstruction en imagerie par résonance magnétique parallèle à l'aide de représentations en ondelettes
No full textTo reduce scanning time or improve spatio-temporal resolution in some MRI applications, parallel MRI acquisition techniques with multiple coils have emerged since the early 90's as powerful methods. In these techniques, MRI images have to be reconstructed from acquired undersampled « k-space » data. To this end, several reconstruction techniques have been proposed such as the widely-used SENSitivity Encoding (SENSE) method. However, the reconstructed images generally present artifacts due to the noise corrupting the observed data and coil sensitivity profile estimation errors. In this work, we present novel SENSE-based reconstruction methods which proceed with regularization in the complex wavelet domain so as to promote the sparsity of the solution. These methods achieve accurate image reconstruction under degraded experimental conditions, in which neither the SENSE method nor standard regularized methods (e.g. Tikhonov) give convincing results. The proposed approaches relies on fast parallel optimization algorithms dealing with convex but non-differentiable criteria involving suitable sparsity promoting priors. Moreover, in contrast with most of the available reconstruction methods which proceed by a slice by slice reconstruction, one of the proposed methods allows 4D (3D + time) reconstruction exploiting spatial and temporal correlations. The hyperparameter estimation problem inherent to the regularization process has also been addressed from a Bayesian viewpoint by using MCMC techniques. Experiments on real anatomical and functional data show that the proposed methods allow us to reduce reconstruction artifacts and improve the statistical sensitivity/specificity in functional MRIPour réduire le temps d'acquisition ou bien améliorer la résolution spatio-temporelle dans certaines application en IRM, de puissantes techniques parallèles utilisant plusieurs antennes réceptrices sont apparues depuis les années 90. Dans ce contexte, les images d'IRM doivent être reconstruites à partir des données sous-échantillonnées acquises dans le « k-space ». Plusieurs approches de reconstruction ont donc été proposées dont la méthode SENSitivity Encoding (SENSE). Cependant, les images reconstruites sont souvent entâchées par des artéfacts dus au bruit affectant les données observées, ou bien à des erreurs d'estimation des profils de sensibilité des antennes. Dans ce travail, nous présentons de nouvelles méthodes de reconstruction basées sur l'algorithme SENSE, qui introduisent une régularisation dans le domaine transformé en ondelettes afin de promouvoir la parcimonie de la solution. Sous des conditions expérimentales dégradées, ces méthodes donnent une bonne qualité de reconstruction contrairement à la méthode SENSE et aux autres techniques de régularisation classique (e.g. Tikhonov). Les méthodes proposées reposent sur des algorithmes parallèles d'optimisation permettant de traiter des critères convexes, mais non nécessairement différentiables contenant des a priori parcimonieux. Contrairement à la plupart des méthodes de reconstruction qui opèrent coupe par coupe, l'une des méthodes proposées permet une reconstruction 4D (3D + temps) en exploitant les corrélations spatiales et temporelles. Le problème d'estimation d'hyperparamètres sous-jacent au processus de régularisation a aussi été traité dans un cadre bayésien en utilisant des techniques MCMC. Une validation sur des données réelles anatomiques et fonctionnelles montre que les méthodes proposées réduisent les artéfacts de reconstruction et améliorent la sensibilité/spécificité statistique en IRM fonctionnell
- …
