Complex networks are an important class of models used to describe the behaviour of a very broad category of systems which appear in different fields of science ranging from physics, biology and statistics to computer science and other disciplines. This set of models includes spin systems on a graph, neural networks, decision networks, spreading disease, financial trade, social networks and all systems which can be represented as interacting agents on some sort of graph architecture. In this thesis, by using the theoretical framework of statistical mechanics, the equilibrium and the dynamical behaviour of such systems is studied. For the equilibrium case, after presenting the region graph free energy approximation, the Survey Propagation method, previously used to investi- gate the low temperature phase of complex systems on tree-like topologies, is extended to the case of loopy graph architectures. For time-dependent behaviour, both discrete-time and continuous-time dynamics are considered. It is shown how to extend the cavity method ap- proach from a tool used to study equilibrium properties of complex systems to the discrete-time dynamical scenario. A closure scheme of the dynamic message-passing equation based on a Markovian approximations is presented. This allows to estimate non-equilibrium marginals of spin models on a graph with reversible dynamics. As an alternative to this approach, an extension of region graph variational free energy approximations to the non-equilibrium case is also presented. Non-equilibrium functionals that, when minimized with constraints, lead to approximate equations for out-of-equilibrium marginals of general spin models are introduced and discussed. For the continuous-time dynamics a novel approach that extends the cav- ity method also to this case is discussed. The main result of this part is a Cavity Master Equation which, together with an approximate version of the Master Equation, constitutes a closure scheme to estimate non-equilibrium marginals of continuous-time spin models. The investigation of dynamics of spin systems is concluded by applying a quasi-equilibrium approach to a sim- ple case. A way to test self-consistently the assumptions of the method as well as its limits is discussed. In the final part of the thesis, analogies and differences between the graph- ical model approaches discussed in the manuscript and causal analysis in statistics are presented. / <p>QC 20160904</p>

Ce travail concerne l'imagerie micro-onde en vue d'application à l'imagerie biomédicale. Cette technique d'imagerie a pour objectif de retrouver la distribution des propriétés diélectriques internes (permittivité diélectrique et conductivité) d'un objet inconnu illuminé par une onde interrogatrice connue à partir des mesures du champ électrique dit diffracté résultant de leur interaction. Un tel problème constitue un problème dit inverse par opposition au problème direct associé qui consiste à calculer le champ diffracté, l'onde interrogatrice et l'objet étant alors connus.La résolution du problème inverse nécessite la construction préalable du modèle direct associé. Celui-ci est ici basé sur une représentation intégrale de domaine des champs électriques donnant naissance à deux équations intégrales couplées dont les contreparties discrètes sont obtenues à l'aide de la méthode des moments. En ce qui concerne le problème inverse, hormis le fait que les équations physiques qui interviennent dans sa modélisation directe le rendent non-linéaire, il est également mathématiquement mal posé au sens de Hadamard, ce qui signifie que les conditions d'existence, d'unicité et de stabilité de la solution ne sont pas simultanément garanties. La résolution d'un tel problème nécessite sa régularisation préalable qui consiste généralement en l'introduction d'information a priori sur la solution recherchée. Cette résolution est effectuée, ici, dans un cadre probabiliste bayésien où l'on introduit une connaissance a priori adaptée à l'objet sous test et qui consiste à considérer ce dernier comme étant composé d'un nombre fini de matériaux homogènes distribués dans des régions compactes. Cet information est introduite par le biais d'un modèle de « Gauss-Markov-Potts ». De plus, le calcul bayésien nous donne la distribution a posteriori de toutes les inconnues connaissant l'a priori et l'objet. On s'attache ensuite à déterminer les estimateurs a posteriori via des méthodes d'approximation variationnelles et à reconstruire ainsi l'image de l'objet recherché. Les principales contributions de ce travail sont d'ordre méthodologique et algorithmique. Elles sont illustrées par une application de l'imagerie micro-onde à la détection du cancer du sein. Cette dernière constitue en soi un point très important et original de la thèse. En effet, la détection du cancer su sein en imagerie micro-onde est une alternative très intéressante à la mammographie par rayons X, mais n'en est encore qu'à un stade exploratoire. / This work concerns the problem of microwave tomography for application to biomedical imaging. The aim is to retreive both permittivity and conductivity of an unknown object from measurements of the scattered field that results from its interaction with a known interrogating wave. Such a problem is said to be inverse opposed to the associated forward problem that consists in calculating the scattered field while the interrogating wave and the object are known. The resolution of the inverse problem requires the prior construction of the associated forward model. This latter is based on an integral representation of the electric field resulting in two coupled integral equations whose discrete counterparts are obtained by means of the method of moments.Regarding the inverse problem, in addition to the fact that the physical equations involved in the forward modeling make it nonlinear, it is also mathematically ill-posed in the sense of Hadamard, which means that the conditions of existence, uniqueness and stability of the solution are not simultaneously guaranteed. Hence, solving this problem requires its prior regularization which usually involves the introduction of a priori information on the sought solution. This resolution is done here in a Bayesian probabilistic framework where we introduced a priori knowledge appropriate to the sought object by considering it to be composed of a finite number of homogeneous materials distributed in compact and homogeneous regions. This information is introduced through a "Gauss-Markov-Potts" model. In addition, the Bayesian computation gives the posterior distribution of all the unknowns, knowing the a priori and the object. We proceed then to identify the posterior estimators via variational approximation methods and thereby to reconstruct the image of the desired object.The main contributions of this work are methodological and algorithmic. They are illustrated by an application of microwave imaging to breast cancer detection. The latter is in itself a very important and original aspect of the thesis. Indeed, the detection of breast cancer using microwave imaging is a very interesting alternative to X-ray mammography, but it is still at an exploratory stage.