Thèses sur le sujet « Apprentissage de représentations (intelligence artificielle) »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleures thèses pour votre recherche sur le sujet « Apprentissage de représentations (intelligence artificielle) ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
Risser-Maroix, Olivier. « Similarité visuelle et apprentissage de représentations ». Electronic Thesis or Diss., Université Paris Cité, 2022. http://www.theses.fr/2022UNIP7327.
Texte intégralThe objective of this CIFRE thesis is to develop an image search engine, based on computer vision, to assist customs officers. Indeed, we observe, paradoxically, an increase in security threats (terrorism, trafficking, etc.) coupled with a decrease in the number of customs officers. The images of cargoes acquired by X-ray scanners already allow the inspection of a load without requiring the opening and complete search of a controlled load. By automatically proposing similar images, such a search engine would help the customs officer in his decision making when faced with infrequent or suspicious visual signatures of products. Thanks to the development of modern artificial intelligence (AI) techniques, our era is undergoing great changes: AI is transforming all sectors of the economy. Some see this advent of "robotization" as the dehumanization of the workforce, or even its replacement. However, reducing the use of AI to the simple search for productivity gains would be reductive. In reality, AI could allow to increase the work capacity of humans and not to compete with them in order to replace them. It is in this context, the birth of Augmented Intelligence, that this thesis takes place. This manuscript devoted to the question of visual similarity is divided into two parts. Two practical cases where the collaboration between Man and AI is beneficial are proposed. In the first part, the problem of learning representations for the retrieval of similar images is still under investigation. After implementing a first system similar to those proposed by the state of the art, one of the main limitations is pointed out: the semantic bias. Indeed, the main contemporary methods use image datasets coupled with semantic labels only. The literature considers that two images are similar if they share the same label. This vision of the notion of similarity, however fundamental in AI, is reductive. It will therefore be questioned in the light of work in cognitive psychology in order to propose an improvement: the taking into account of visual similarity. This new definition allows a better synergy between the customs officer and the machine. This work is the subject of scientific publications and a patent. In the second part, after having identified the key components allowing to improve the performances of thepreviously proposed system, an approach mixing empirical and theoretical research is proposed. This secondcase, augmented intelligence, is inspired by recent developments in mathematics and physics. First applied tothe understanding of an important hyperparameter (temperature), then to a larger task (classification), theproposed method provides an intuition on the importance and role of factors correlated to the studied variable(e.g. hyperparameter, score, etc.). The processing chain thus set up has demonstrated its efficiency byproviding a highly explainable solution in line with decades of research in machine learning. These findings willallow the improvement of previously developed solutions
Tamaazousti, Youssef. « Vers l’universalité des représentations visuelle et multimodales ». Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC038/document.
Texte intégralBecause 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
Franceschi, Jean-Yves. « Apprentissage de représentations et modèles génératifs profonds dans les systèmes dynamiques ». Electronic Thesis or Diss., Sorbonne université, 2022. http://www.theses.fr/2022SORUS014.
Texte intégralThe recent rise of deep learning has been motivated by numerous scientific breakthroughs, particularly regarding representation learning and generative modeling. However, most of these achievements have been obtained on image or text data, whose evolution through time remains challenging for existing methods. Given their importance for autonomous systems to adapt in a constantly evolving environment, these challenges have been actively investigated in a growing body of work. In this thesis, we follow this line of work and study several aspects of temporality and dynamical systems in deep unsupervised representation learning and generative modeling. Firstly, we present a general-purpose deep unsupervised representation learning method for time series tackling scalability and adaptivity issues arising in practical applications. We then further study in a second part representation learning for sequences by focusing on structured and stochastic spatiotemporal data: videos and physical phenomena. We show in this context that performant temporal generative prediction models help to uncover meaningful and disentangled representations, and conversely. We highlight to this end the crucial role of differential equations in the modeling and embedding of these natural sequences within sequential generative models. Finally, we more broadly analyze in a third part a popular class of generative models, generative adversarial networks, under the scope of dynamical systems. We study the evolution of the involved neural networks with respect to their training time by describing it with a differential equation, allowing us to gain a novel understanding of this generative model
Bourigault, Simon. « Apprentissage de représentations pour la prédiction de propagation d'information dans les réseaux sociaux ». Electronic Thesis or Diss., Paris 6, 2016. http://www.theses.fr/2016PA066368.
Texte intégralIn 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
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.
Texte intégralIn 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
Ferré, Arnaud. « Représentations vectorielles et apprentissage automatique pour l’alignement d’entités textuelles et de concepts d’ontologie : application à la biologie ». Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS117/document.
Texte intégralThe impressive increase in the quantity of textual data makes it difficult today to analyze them without the assistance of tools. However, a text written in natural language is unstructured data, i.e. it cannot be interpreted by a specialized computer program, without which the information in the texts remains largely under-exploited. Among the tools for automatic extraction of information from text, we are interested in automatic text interpretation methods for the entity normalization task that consists in automatically matching text entitiy mentions to concepts in a reference terminology. To accomplish this task, we propose a new approach by aligning two types of vector representations of entities that capture part of their meanings: word embeddings for text mentions and concept embeddings for concepts, designed specifically for this work. The alignment between the two is done through supervised learning. The developed methods have been evaluated on a reference dataset from the biological domain and they now represent the state of the art for this dataset. These methods are integrated into a natural language processing software suite and the codes are freely shared
Poussevin, Mickael. « Apprentissage de représentation pour des données générées par des utilisateurs ». Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066040/document.
Texte intégralIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
Francis, Danny. « Représentations sémantiques d'images et de vidéos ». Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS605.
Texte intégralRecent research in Deep Learning has sent the quality of results in multimedia tasks rocketing: thanks to new big datasets of annotated images and videos, Deep Neural Networks (DNN) have outperformed other models in most cases. In this thesis, we aim at developing DNN models for automatically deriving semantic representations of images and videos. In particular we focus on two main tasks : vision-text matching and image/video automatic captioning. Addressing the matching task can be done by comparing visual objects and texts in a visual space, a textual space or a multimodal space. Based on recent works on capsule networks, we define two novel models to address the vision-text matching problem: Recurrent Capsule Networks and Gated Recurrent Capsules. In image and video captioning, we have to tackle a challenging task where a visual object has to be analyzed, and translated into a textual description in natural language. For that purpose, we propose two novel curriculum learning methods. Moreover regarding video captioning, analyzing videos requires not only to parse still images, but also to draw correspondences through time. We propose a novel Learned Spatio-Temporal Adaptive Pooling method for video captioning that combines spatial and temporal analysis. Extensive experiments on standard datasets assess the interest of our models and methods with respect to existing works
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.
Texte intégralThe 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
Poussevin, Mickael. « Apprentissage de représentation pour des données générées par des utilisateurs ». Electronic Thesis or Diss., Paris 6, 2015. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2015PA066040.pdf.
Texte intégralIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
Scherrer, Bruno. « Apprentissage de représentation et auto-organisation modulaire pour un agent autonome ». Phd thesis, Université Henri Poincaré - Nancy I, 2003. http://tel.archives-ouvertes.fr/tel-00003377.
Texte intégralNous avons considéré trois problèmes de complexité croissante et montré qu'ils admettaient des solutions algorithmiques connexionnistes : 1) L'apprentissage par renforcement dans un petit espace d'états : nous nous appuyons sur un algorithme de la littérature pour construire un réseau connexionniste ; les paramètres du problème sont stockés par les poids des unités et des connexions et le calcul du plan est le résultat d'une activité distribuée dans le réseau. 2) L'apprentissage d'une représentation pour approximer un problème d'apprentissage par renforcement ayant un grand espace d'états : nous automatisons le procédé consistant à construire une partition de l'espace d'états pour approximer un problème de grande taille. 3) L'auto-organisation en modules spécialisés pour approximer plusieurs problèmes d'apprentissage par renforcement ayant un grand espace d'états : nous proposons d'exploiter le principe "diviser pour régner" et montrons comment plusieurs tâches peuvent être réparties efficacement sur un petit nombre de modules fonctionnels spécialisés.
Bredèche, Nicolas. « Ancrage de lexique et perceptions : changements de représentation et apprentissage dans le contexte d'un agent situé et mobile ». Paris 11, 2002. http://www.theses.fr/2002PA112225.
Texte intégralIn Artificial Intelligence, the symbol grounding problem is considered as an important issue regarding the meaning of symbols used by an artificial agent. Our work is concerned with the grounding of symbols for a situated mobile robot that navigates through a real world environment. In this setting, the main problem the robot encounters is to ground symbols given by a human teacher that refers to physical entities (e. G. A door, a human, etc. ). Grounding such a lexicon is a difficult task because of the intrinsic nature of the environment: it is dynamic, complex and noisy. Moreover, one specific symbol (e. G. "door") may refer to different physical objects in size, shape or colour while the robot may acquire only a small number of examples for each symbol. Also, it is not possible to rely on ad-hoc physical models of symbols due to the great number of symbols that may be grounded. Thus, the problem is to define how to build a grounded representation in such a context. In order to address this problem, we have reformulated the symbol grounding problem as a supervised learning problem. We present an approach that relies on the use of abstraction operators. Thanks to these operators, information on granularity and structural configuration is extracted from the perceptions in order to case the building of an anchor. For each symbol, the appropriate definition for these operators is found out thanks to successive changes of representation that provide an efficient and adapted anchor. In order to implement our approach, we have developed PLIC and WMplic which are successfully used for long term symbol grounding by a PIONEER2 DX mobile robot in the corridors of the Computer Sciences Lab of the University of Paris 6
Jouffroy, Emma. « Développement de modèles non supervisés pour l'obtention de représentations latentes interprétables d'images ». Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0050.
Texte intégralThe Laser Megajoule (LMJ) is a large research device that simulates pressure and temperature conditions similar to those found in stars. During experiments, diagnostics are guided into an experimental chamber for precise positioning. To minimize the risks associated with human error in such an experimental context, the automation of an anti-collision system is envisaged. This involves the design of machine learning tools offering reliable decision levels based on the interpretation of images from cameras positioned in the chamber. Our research focuses on probabilistic generative neural methods, in particular variational auto-encoders (VAEs). The choice of this class of models is linked to the fact that it potentially enables access to a latent space directly linked to the properties of the objects making up the observed scene. The major challenge is to study the design of deep network models that effectively enable access to such a fully informative and interpretable representation, with a view to system reliability. The probabilistic formalism intrinsic to VAE allows us, if we can trace back to such a representation, to access an analysis of the uncertainties of the encoded information
Dutech, Alain. « Apprentissage par Renforcement : Au delà des Processus Décisionnels de Markov (Vers la cognition incarnée) ». Habilitation à diriger des recherches, Université Nancy II, 2010. http://tel.archives-ouvertes.fr/tel-00549108.
Texte intégralDenize, Julien. « Self-supervised representation learning and applications to image and video analysis ». Electronic Thesis or Diss., Normandie, 2023. http://www.theses.fr/2023NORMIR37.
Texte intégralIn this thesis, we develop approaches to perform self-supervised learning for image and video analysis. Self-supervised representation learning allows to pretrain neural networks to learn general concepts without labels before specializing in downstream tasks faster and with few annotations. We present three contributions to self-supervised image and video representation learning. First, we introduce the theoretical paradigm of soft contrastive learning and its practical implementation called Similarity Contrastive Estimation (SCE) connecting contrastive and relational learning for image representation. Second, SCE is extended to global temporal video representation learning. Lastly, we propose COMEDIAN a pipeline for local-temporal video representation learning for transformers. These contributions achieved state-of-the-art results on multiple benchmarks and led to several academic and technical published contributions
Loutchmia, Dominique. « Une méthode d'analyse discriminante pour des concepts imprécis ». Phd thesis, Université de la Réunion, 1998. http://tel.archives-ouvertes.fr/tel-00473292.
Texte intégralMagnan, Jean-Christophe. « Représentations graphiques de fonctions et processus décisionnels Markoviens factorisés ». Electronic Thesis or Diss., Paris 6, 2016. http://www.theses.fr/2016PA066042.
Texte intégralIn 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
Lesaint, Florian. « Modélisation du conditionnement animal par représentations factorisées dans un système d'apprentissage dual : explication des différences inter-individuelles aux niveaux comportemental et neurophysiologique ». Electronic Thesis or Diss., Paris 6, 2014. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2014PA066287.pdf.
Texte intégralPavlovian conditioning, the acquisition of responses to neutral stimuli previously paired with rewards, and instrumental conditioning, the acquisition of goal-oriented responses, are central to our learning capacities. However, despite some evidences of entanglement, they are mainly studied separately. Reinforcement learning (RL), learning by trials and errors to reach goals, is central to models of instrumental conditioning, while models of Pavlovian conditioning rely on more dedicated and often incompatible architectures. This complicates the study of their interactions. We aim at finding concepts which combined with RL models may provide a unifying architecture to allow such a study. We develop a model that combines a classical RL system, learning values over states, with a revised RL system, learning values over individual stimuli and biasing the behaviour towards reward-related ones. It explains maladaptive behaviours in pigeons by the detrimental interaction of systems, and inter-individual differences in rats by a simple variation at the population level in the contribution of each system to the overall behaviour. It explains unexpected dopaminergic patterns with regard to the dominant hypothesis that dopamine parallels a reward prediction error signal by computing such signal over features rather than states, and makes it compatible with an alternative hypothesis that dopamine also contributes to the acquisition of incentive salience, making reward-related stimuli wanted for themselves. The present model shows promising properties for the investigation of Pavlovian conditioning, instrumental conditioning and their interactions
Carvalho, Micael. « Deep representation spaces ». Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS292.
Texte intégralIn recent years, Deep Learning techniques have swept the state-of-the-art of many applications of Machine Learning, becoming the new standard approach for them. The architectures issued from these techniques have been used for transfer learning, which extended the power of deep models to tasks that did not have enough data to fully train them from scratch. This thesis' subject of study is the representation spaces created by deep architectures. First, we study properties inherent to them, with particular interest in dimensionality redundancy and precision of their features. Our findings reveal a strong degree of robustness, pointing the path to simple and powerful compression schemes. Then, we focus on refining these representations. We choose to adopt a cross-modal multi-task problem, and design a loss function capable of taking advantage of data coming from multiple modalities, while also taking into account different tasks associated to the same dataset. In order to correctly balance these losses, we also we develop a new sampling scheme that only takes into account examples contributing to the learning phase, i.e. those having a positive loss. Finally, we test our approach in a large-scale dataset of cooking recipes and associated pictures. Our method achieves a 5-fold improvement over the state-of-the-art, and we show that the multi-task aspect of our approach promotes a semantically meaningful organization of the representation space, allowing it to perform subtasks never seen during training, like ingredient exclusion and selection. The results we present in this thesis open many possibilities, including feature compression for remote applications, robust multi-modal and multi-task learning, and feature space refinement. For the cooking application, in particular, many of our findings are directly applicable in a real-world context, especially for the detection of allergens, finding alternative recipes due to dietary restrictions, and menu planning
Magnan, Jean-Christophe. « Représentations graphiques de fonctions et processus décisionnels Markoviens factorisés ». Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066042/document.
Texte intégralIn 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
Fois, Adrien. « Plasticité et codage temporel dans les réseaux impulsionnels appliqués à l'apprentissage de représentations ». Electronic Thesis or Diss., Université de Lorraine, 2022. http://www.theses.fr/2022LORR0299.
Texte intégralNeuromorphic computing is a rapidly growing field of computer science. It seeks to define models of computation inspired by the properties of the brain. Neuromorphic computing redefines the nature of the three key components of learning: 1) data, 2) computing substrate, and 3) algorithms, based on how the brain works. First, the data are represented with all-or-nothing events distributed in space and time: spikes. Second, the computational substrate erases the separation between computation and memory introduced by Von Neumann architectures by co-locating them, as in the brain. Furthermore, the computation is massively parallel and asynchronous allowing the computational units to be activated on the fly, independently. Third, the learning algorithms are adapted to the computing substrate by exploiting the information available locally, at the neuron level. This vast overhaul in the way information transfer, information representation, computation and learning are approached, allows neuromorphic processors to promise in particular an energy saving of a considerable factor of 100 to 1000 compared to CPUs. In this thesis, we explore the algorithmic side of neuromorphic computing by proposing event-driven learning rules that satisfy locality constraints and are capable of extracting representations of event-based, sparse and asynchronous data streams. Moreover, while most related studies are based on rate codes where information is exclusively represented in the number of spikes, our learning rules exploit much more efficient temporal codes, where information is contained in the spike times. We first propose an in-depth analysis of a temporal coding method using a population of neurons. We propose a decoding method and we analyze the delivered information and the code structure. Then we introduce a new event-driven and local rule capable of extracting representations from temporal codes by storing centroids in a distributed way within the synaptic weights of a neural population. We then propose to learn representations not in synaptic weights, but rather in transmission delays operating intrinsically in the temporal dimension. This led to two new event-driven and local rules. One rule adapts delays so as to store representations, the other rule adapts weights so as to filter features according to their temporal variability. The two rules operate complementarily. In a last model, these rules adapting weights and delays are augmented by a new spatio-temporal neuromodulator. This neuromodulator makes it possible for the model to reproduce the behavior of self-organizing maps with spiking neurons, thus leading to the generation of ordered maps during the learning of representations. Finally, we propose a new generic labeling and voting method designed for spiking neural networks dealing with temporal codes. This method is used so as to evaluate our last model in the context of categorization tasks
Mita, Graziano. « Toward interpretable machine learning, with applications to large-scale industrial systems data ». Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS112.
Texte intégralThe contributions presented in this work are two-fold. We first provide a general overview of explanations and interpretable machine learning, making connections with different fields, including sociology, psychology, and philosophy, introducing a taxonomy of popular explainability approaches and evaluation methods. We subsequently focus on rule learning, a specific family of transparent models, and propose a novel rule-based classification approach, based on monotone Boolean function synthesis: LIBRE. LIBRE is an ensemble method that combines the candidate rules learned by multiple bottom-up learners with a simple union, in order to obtain a final intepretable rule set. Our method overcomes most of the limitations of state-of-the-art competitors: it successfully deals with both balanced and imbalanced datasets, efficiently achieving superior performance and higher interpretability in real datasets. Interpretability of data representations constitutes the second broad contribution to this work. We restrict our attention to disentangled representation learning, and, in particular, VAE-based disentanglement methods to automatically learn representations consisting of semantically meaningful features. Recent contributions have demonstrated that disentanglement is impossible in purely unsupervised settings. Nevertheless, incorporating inductive biases on models and data may overcome such limitations. We present a new disentanglement method - IDVAE - with theoretical guarantees on disentanglement, deriving from the employment of an optimal exponential factorized prior, conditionally dependent on auxiliary variables complementing input observations. We additionally propose a semi-supervised version of our method. Our experimental campaign on well-established datasets in the literature shows that IDVAE often beats its competitors according to several disentanglement metrics
Bergeron, Jean. « Modélisation du processus cognitif associé à l'introduction de nouvelles technologies dans une organisation : amélioration de la capacité d'apprentissage organisationnel technologique ». Châtenay-Malabry, Ecole centrale de Paris, 1996. http://www.theses.fr/1996ECAP0496.
Texte intégralElguendouze, Sofiane. « Explainable Artificial Intelligence approaches for Image Captioning ». Electronic Thesis or Diss., Orléans, 2024. http://www.theses.fr/2024ORLE1003.
Texte intégralThe rapid advancement of image captioning models, driven by the integration of deep learning techniques that combine image and text modalities, has resulted in increasingly complex systems. However, these models often operate as black boxes, lacking the ability to provide transparent explanations for their decisions. This thesis addresses the explainability of image captioning systems based on Encoder-Attention-Decoder architectures, through four aspects. First, it explores the concept of the latent space, marking a departure from traditional approaches relying on the original representation space. Second, it introduces the notion of decisiveness, leading to the formulation of a new definition for the concept of component influence/decisiveness in the context of explainable image captioning, as well as a perturbation-based approach to capturing decisiveness. The third aspect aims to elucidate the factors influencing explanation quality, in particular the scope of explanation methods. Accordingly, latent-based variants of well-established explanation methods such as LRP and LIME have been developed, along with the introduction of a latent-centered evaluation approach called Latent Ablation. The fourth aspect of this work involves investigating what we call saliency and the representation of certain visual concepts, such as object quantity, at different levels of the captioning architecture
Merckling, Astrid. « Unsupervised pretraining of state representations in a rewardless environment ». Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS141.
Texte intégralThis thesis seeks to extend the capabilities of state representation learning (SRL) to help scale deep reinforcement learning (DRL) algorithms to continuous control tasks with high-dimensional sensory observations (such as images). SRL allows to improve the performance of DRL by providing it with better inputs than the input embeddings learned from scratch with end-to-end strategies. Specifically, this thesis addresses the problem of performing state estimation in the manner of deep unsupervised pretraining of state representations without reward. These representations must verify certain properties to allow for the correct application of bootstrapping and other decision making mechanisms common to supervised learning, such as being low-dimensional and guaranteeing the local consistency and topology (or connectivity) of the environment, which we will seek to achieve through the models pretrained with the two SRL algorithms proposed in this thesis
Lesaint, Florian. « Modélisation du conditionnement animal par représentations factorisées dans un système d'apprentissage dual : explication des différences inter-individuelles aux niveaux comportemental et neurophysiologique ». Thesis, Paris 6, 2014. http://www.theses.fr/2014PA066287/document.
Texte intégralPavlovian conditioning, the acquisition of responses to neutral stimuli previously paired with rewards, and instrumental conditioning, the acquisition of goal-oriented responses, are central to our learning capacities. However, despite some evidences of entanglement, they are mainly studied separately. Reinforcement learning (RL), learning by trials and errors to reach goals, is central to models of instrumental conditioning, while models of Pavlovian conditioning rely on more dedicated and often incompatible architectures. This complicates the study of their interactions. We aim at finding concepts which combined with RL models may provide a unifying architecture to allow such a study. We develop a model that combines a classical RL system, learning values over states, with a revised RL system, learning values over individual stimuli and biasing the behaviour towards reward-related ones. It explains maladaptive behaviours in pigeons by the detrimental interaction of systems, and inter-individual differences in rats by a simple variation at the population level in the contribution of each system to the overall behaviour. It explains unexpected dopaminergic patterns with regard to the dominant hypothesis that dopamine parallels a reward prediction error signal by computing such signal over features rather than states, and makes it compatible with an alternative hypothesis that dopamine also contributes to the acquisition of incentive salience, making reward-related stimuli wanted for themselves. The present model shows promising properties for the investigation of Pavlovian conditioning, instrumental conditioning and their interactions
Paudel, Subodh. « Methodology to estimate building energy consumption using artificial intelligence ». Thesis, Nantes, Ecole des Mines, 2016. http://www.theses.fr/2016EMNA0237/document.
Texte intégralHigh-energy efficiency building standards (as Low energy building LEB) to improve building consumption have drawn significant attention. Building standards is basically focused on improving thermal performance of envelope and high heat capacity thus creating a higher thermal inertia. However, LEB concept introduces alarge time constant as well as large heat capacity resulting in a slower rate of heat transfer between interior of building and outdoor environment. Therefore, it is challenging to estimate and predict thermal energy demand for such LEBs. This work focuses on artificial intelligence (AI) models to predict energy consumptionof LEBs. We consider two kinds of AI modeling approaches: “all data” and “relevant data”. The “all data” uses all available data and “relevant data” uses a small representative day dataset and addresses the complexity of building non-linear dynamics by introducing past day climatic impacts behavior. This extraction is based on either simple physical understanding: Heating Degree Day (HDD), modified HDD or pattern recognition methods: Frechet Distance and Dynamic Time Warping (DTW). Four AI techniques have been considered: Artificial Neural Network (ANN), Support Vector Machine (SVM), Boosted Ensemble Decision Tree (BEDT) and Random forest (RF). In a first part, numerical simulations for six buildings (heat demand in the range [25 – 85 kWh/m².yr]) have been performed. The approach “relevant data” with (DTW, SVM) shows the best results. Real data of the building “Ecole des Mines de Nantes” proves the approach is still relevant
Ben-Younes, Hedi. « Multi-modal representation learning towards visual reasoning ». Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS173.
Texte intégralThe quantity of images that populate the Internet is dramatically increasing. It becomes of critical importance to develop the technology for a precise and automatic understanding of visual contents. As image recognition systems are becoming more and more relevant, researchers in artificial intelligence now seek for the next generation vision systems that can perform high-level scene understanding. In this thesis, we are interested in Visual Question Answering (VQA), which consists in building models that answer any natural language question about any image. Because of its nature and complexity, VQA is often considered as a proxy for visual reasoning. Classically, VQA architectures are designed as trainable systems that are provided with images, questions about them and their answers. To tackle this problem, typical approaches involve modern Deep Learning (DL) techniques. In the first part, we focus on developping multi-modal fusion strategies to model the interactions between image and question representations. More specifically, we explore bilinear fusion models and exploit concepts from tensor analysis to provide tractable and expressive factorizations of parameters. These fusion mechanisms are studied under the widely used visual attention framework: the answer to the question is provided by focusing only on the relevant image regions. In the last part, we move away from the attention mechanism and build a more advanced scene understanding architecture where we consider objects and their spatial and semantic relations. All models are thoroughly experimentally evaluated on standard datasets and the results are competitive with the literature
Sangnier, Maxime. « Outils d'apprentissage automatique pour la reconnaissance de signaux temporels ». Rouen, 2015. http://www.theses.fr/2015ROUES064.
Texte intégralThe work presented here tackles two different subjects in the wide thematic of how to build a numerical system to recognize temporal signals, mainly from limited observations. The first one is automatic feature extraction. For this purpose, we present a column generation algorithm, which is able to jointly learn a discriminative Time-Frequency (TF) transform, cast as a filter bank, with a support vector machine. This algorithm extends the state of the art on multiple kernel learning by non-linearly combining an infinite amount of kernels. The second direction of research is the way to handle the temporal nature of the signals. While our first contribution pointed out the importance of correctly choosing the time resolution to get a discriminative TF representation, the role of the time is clearly enlightened in early recognition of signals. Our second contribution lies in this field and introduces a methodological framework for early detection of a special event in a time-series, that is detecting an event before it ends. This framework builds upon multiple instance learning and similarity spaces by fitting them to the particular case of temporal sequences. Furthermore, our early detector comes with an efficient learning algorithm and theoretical guarantees on its generalization ability. Our two contributions have been empirically evaluated with brain-computer interface signals, soundscapes and human actions movies
Banville, Hubert. « Enabling real-world EEG applications with deep learning ». Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPASG005.
Texte intégralOur understanding of the brain has improved considerably in the last decades, thanks to groundbreaking advances in the field of neuroimaging. Now, with the invention and wider availability of personal wearable neuroimaging devices, such as low-cost mobile EEG, we have entered an era in which neuroimaging is no longer constrained to traditional research labs or clinics. "Real-world'' EEG comes with its own set of challenges, though, ranging from a scarcity of labelled data to unpredictable signal quality and limited spatial resolution. In this thesis, we draw on the field of deep learning to help transform this century-old brain imaging modality from a purely clinical- and research-focused tool, to a practical technology that can benefit individuals in their day-to-day life. First, we study how unlabelled EEG data can be utilized to gain insights and improve performance on common clinical learning tasks using self-supervised learning. We present three such self-supervised approaches that rely on the temporal structure of the data itself, rather than onerously collected labels, to learn clinically-relevant representations. Through experiments on large-scale datasets of sleep and neurological screening recordings, we demonstrate the significance of the learned representations, and show how unlabelled data can help boost performance in a semi-supervised scenario. Next, we explore ways to ensure neural networks are robust to the strong sources of noise often found in out-of-the-lab EEG recordings. Specifically, we present Dynamic Spatial Filtering, an attention mechanism module that allows a network to dynamically focus its processing on the most informative EEG channels while de-emphasizing any corrupted ones. Experiments on large-scale datasets and real-world data demonstrate that, on sparse EEG, the proposed attention block handles strong corruption better than an automated noise handling approach, and that the predicted attention maps can be interpreted to inspect the functioning of the neural network. Finally, we investigate how weak labels can be used to develop a biomarker of neurophysiological health from real-world EEG. We translate the brain age framework, originally developed using lab and clinic-based magnetic resonance imaging, to real-world EEG data. Using recordings from more than a thousand individuals performing a focused attention exercise or sleeping overnight, we show not only that age can be predicted from wearable EEG, but also that age predictions encode information contained in well-known brain health biomarkers, but not in chronological age. Overall, this thesis brings us a step closer to harnessing EEG for neurophysiological monitoring outside of traditional research and clinical contexts, and opens the door to new and more flexible applications of this technology
Sobral, Rui. « Techniques et systèmes d'acquisition des connaissances ». Compiègne, 1989. http://www.theses.fr/1989COMPD168.
Texte intégralFilippi, Sarah. « Stratégies optimistes en apprentissage par renforcement ». Phd thesis, Ecole nationale supérieure des telecommunications - ENST, 2010. http://tel.archives-ouvertes.fr/tel-00551401.
Texte intégralQiu, Mingming. « Designing smart home services using machine learning and knowledge-based approaches ». Electronic Thesis or Diss., Institut polytechnique de Paris, 2023. http://www.theses.fr/2023IPPAT014.
Texte intégralThe intelligence of a smart home is realized by creating various services. Eachservice tries to adjust one monitored state by controlling related actuators after consideringenvironment states detected by sensors. However, the design of the logic of the services deployedin a smart home faces limitations of either dynamic adaptability (predefined rules) orexplicability (learning techniques). Four proposals that are parts of a hybrid approach combiningpredefined rules and learning techniques aim at mitigating these limitations.The first proposal is to use reinforcement learning to create a dynamic service. The deploymentof this single service includes two phases : pretraining in the simulation and continuous trainingin the real world. Our study only focuses on the simulation part. Extending the first proposal,the second proposal proposes several architectures to create multiple dynamic and conflictfreeservices. However, the created data-driven services are not explicable. Therefore, the thirdproposal aims to extract explicable knowledgebased services from dynamic data-driven services.The fourth proposal attempts to combine the second and third proposals to create dynamicand explicable services. These proposals are evaluated in a simulated environment ontemperature control, light intensity, and air quality services adapted to the activities of the inhabitant.They can be extended according to several perspectives, such as the co-simulation ofphysical phenomena, the dynamic adaptation to various inhabitant profiles, and the energy efficiencyof the deployed services
Wynen, Daan. « Une représentation archétypale de style artistique : résumer et manipuler des stylesartistiques d'une façon interprétable ». Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM066.
Texte intégralIn this thesis we study the representations used to describe and manipulate artistic style of visual arts.In the neural style transfer literature and related strains of research, different representations have been proposed, but in recent years the by far dominant representations of artistic style in the computer vision community have been those learned by deep neural networks, trained on natural images.We build on these representations with the dual goal of summarizing the artistic styles present in large collections of digitized artworks, as well as manipulating the styles of images both natural and artistic.To this end, we propose a concise and intuitive representation based on archetypal analysis, a classic unsupervised learning method with properties that make it especially suitable for the task. We demonstrate how this archetypal representation of style can be used to discover and describe, in an interpretable way, which styles are present in a large collection.This enables the exploration of styles present in a collection from different angles; different ways of visualizing the information allow for different questions to be asked.These can be about a style that was identified across artworks, about the style of a particular artwork, or more broadly about how the styles that were identified relate to one another.We apply our analysis to a collection of artworks obtained from WikiArt, an online collection effort of visual arts driven by volunteers. This dataset also includes metadata such as artist identies, genre, and style of the artworks. We use this metadata for further analysis of the archetypal style representation along biographic lines of artists and with an eye on the relationships within groups of artists
Zanuttini, Bruno. « Acquisition de connaissances et raisonnement en logique propositionnelle ». Phd thesis, Université de Caen, 2003. http://tel.archives-ouvertes.fr/tel-00995247.
Texte intégralPoezevara, Guillaume. « Fouille de graphes pour la découverte de contrastes entre classes : application à l'estimation de la toxicité des molécules ». Phd thesis, Université de Caen, 2011. http://tel.archives-ouvertes.fr/tel-01018425.
Texte intégralKahindo, Senge Muvingi Christian. « Analyse automatique de l’écriture manuscrite sur tablette pour la détection et le suivi thérapeutique de personnes présentant des pathologies ». Electronic Thesis or Diss., Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLL016.
Texte intégralWe 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
Venturini, Gilles. « Apprentissage adaptatif et apprentissage supervise par algorithme genetique ». Paris 11, 1994. http://www.theses.fr/1994PA112016.
Texte intégralGreboval, Marie-Hélène. « La production d'explications, vue comme une tâche de conception : contribution au projet AIDE ». Compiègne, 1994. http://www.theses.fr/1994COMPD752.
Texte intégralCharnay, Clément. « Enhancing supervised learning with complex aggregate features and context sensitivity ». Thesis, Strasbourg, 2016. http://www.theses.fr/2016STRAD025/document.
Texte intégralIn this thesis, we study model adaptation in supervised learning. Firstly, we adapt existing learning algorithms to the relational representation of data. Secondly, we adapt learned prediction models to context change.In the relational setting, data is modeled by multiples entities linked with relationships. We handle these relationships using complex aggregate features. We propose stochastic optimization heuristics to include complex aggregates in relational decision trees and Random Forests, and assess their predictive performance on real-world datasets.We adapt prediction models to two kinds of context change. Firstly, we propose an algorithm to tune thresholds on pairwise scoring models to adapt to a change of misclassification costs. Secondly, we reframe numerical attributes with affine transformations to adapt to a change of attribute distribution between a learning and a deployment context. Finally, we extend these transformations to complex aggregates
Mephu-Nguifo, Engelbert. « Concevoir une abstraction à partir de ressemblances ». Montpellier 2, 1993. http://www.theses.fr/1993MON20065.
Texte intégralEngilberge, Martin. « Deep Inside Visual-Semantic Embeddings ». Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS150.
Texte intégralNowadays Artificial Intelligence (AI) is omnipresent in our society. The recentdevelopment of learning methods based on deep neural networks alsocalled "Deep Learning" has led to a significant improvement in visual representation models.and textual.In this thesis, we aim to further advance image representation and understanding.Revolving around Visual Semantic Embedding (VSE) approaches, we explore different directions: We present relevant background covering images and textual representation and existing multimodal approaches. We propose novel architectures further improving retrieval capability of VSE and we extend VSE models to novel applications and leverage embedding models to visually ground semantic concept. Finally, we delve into the learning process andin particular the loss function by learning differentiable approximation of ranking based metric
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.
Texte intégralWe 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
Poittevin, Luc. « Un outil générique de conception et de révision coopérative de Bases de Connaissances s'appuyant sur la notion de situation ». Phd thesis, Université Paris Sud - Paris XI, 1998. http://tel.archives-ouvertes.fr/tel-00941692.
Texte intégralNapoli, Amedeo. « Représentations à objets et raisonnement par classification en intelligence artificielle ». Nancy 1, 1992. http://www.theses.fr/1992NAN10012.
Texte intégralHelft, Nicolas. « L' Induction en intelligence artificielle : théorie et algorithmes ». Aix-Marseille 2, 1988. http://www.theses.fr/1988AIX22044.
Texte intégralEl, hamzaoui Imane. « Unsupervised separation of sparse multivalued components with applications in astrophysics ». Electronic Thesis or Diss., université Paris-Saclay, 2020. http://www.theses.fr/2020UPASG015.
Texte intégralThe rapid increase of multispectral-multitemporal imagers in various application fields requires new data analysis tools particularly suitable for multivalued data. In high-energy astronomy, missions such as Chandra or Fermi are telling examples of signal processing challenges past or to come. This thesis is aimed at proposing new models to analyze X-ray astrophysical data and introducing efficient algorithms to retrieve meaningful information from these data. More specifically, the goal of this thesis is to extend component separation techniques in order to propose models that faithfully describe measurements contaminated with shot noise and that fully account for spectral variabilities ubiquitous in high-energy astrophysical images. The numerical tools developed in this thesis will be applied to X-ray Chandra telescope data
Kinauer, Stefan. « Représentations à base de parties pour la vision 3D de haut niveau ». Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC059/document.
Texte intégralIn this work we use Deformable Part Models (DPMs) to learn and detect object parts in 3 dimensions. Given a single RGB image of an object, the objective is to determine the location of the object’s parts. The resulting optimization problem is non-convex and challenging due to its large solution space.Our first contribution consists in extending DPMs into the third dimension through an efficient Branch-and-Bound algorithm. We devise a customized algorithm that is two orders of magnitude faster than a naive approach and guarantees global-optimality. We derive the model’s 3-dimensional geometry from one 3-dimensional structure, but train viewpoint-specific part appearance terms based on deep learning features. We demonstrate our approach on the task of 3D object pose estimation, determining the object pose within a fraction of a second.Our second contribution allows us to perform efficient inference with part-based models where the part connections form a graph with loops, thereby allowing for richer models. For this, we use the Alternating Direction Method of Multipliers (ADMM) to decouple the problem and solve iteratively a set of easier sub-problems. We compute 3-dimensional model parameters in a Convolutional Neural Network for 3D human pose estimation. Then we append the developed inference algorithm as final layer to this neural network. This yields state of the art performance in the 3D human pose estimation task
Collain, Emmanuel, et Jean-Marc Fovet. « Apprentissage de plans de résolution pour améliorer l'efficacité des chainages avant des systèmes à base de règles ». Paris 6, 1991. http://www.theses.fr/1991PA066446.
Texte intégralFouladi, Karan. « Recommandation multidimensionnelle d’émissions télévisées par apprentissage : Une interface de visualisation intelligente pour la télévision numérique ». Paris 6, 2013. http://www.theses.fr/2013PA066040.
Texte intégralDue to the wealth of entertainment contents provided by Digital Mass Media and in particular by Digital Television (satellite, cable, terrestrial or IP), choosing a program has become more and more difficult. Far from having a user-friendly environment, Digital Television (DTV) users face a huge choice of content, assisted only by off-putting interfaces named classical "Electronic Program Guide" EPG. That makes users' attention blurry and decreases their active program searching and choice. The central topic of this thesis is the development of a Recommendation System interfaced mapping interactive TV content. To do this, we chose to use a Recommendation System based on the content and have adapted to the field of television. This adaptation is carried out at several specific steps. We especially worked processing metadata associated with television content and developing an expert system can provide us with a unique categorization of television. We also took the initiative to model and integrate the context of use in our television viewing environment modeling. The integration of context allowed us to obtain a sufficiently fine and stable in this environment, allowing us to implementing our recommendation system. Detailed categorization of metadata associated with television content and modeling & integration of context of use television is the main contribution of this thesis. To assess / improve our developments, we installed a fleet of nine homes left in three specific types of families. This has given us the means to assess the contribution of our work in ease of use television in real conditions of use. By an implicit approach, we apprehended the behavior of television families (involved in our project) vis-à-vis television content. A syntactic-semantic analyzer has provided a measure of gradual interest thereon to the content, for each family. We have also developed an interactive mapping interface based on the idea of "Island of memory" for the interactive interface is in line with Recommendation System in place. Our recommendation system based on content and assisted learning (reinforcement learning), has provided us with the most optimal results to the scientific community in the field