Dissertations / Theses on the topic 'Apprentissage invariant'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 15 dissertations / theses for your research on the topic 'Apprentissage invariant.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Moummad, Ilyass. "Invariant representation learning for few-shot bioacoustic event detection and classification." Electronic Thesis or Diss., Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2024. http://www.theses.fr/2024IMTA0442.
Full textThis thesis focuses on developing robust and transferable representation learning techniques for few-shot bioacoustic event detection and classification, addressing core challenges in deep learning such as domain generalization, domain adaptation, data scarcity, and class imbalance. Through the exploration of self-supervised invariant representation learning, we demonstrate that domain-agnostic data augmentations can yield informative and discriminative representations. A key focus of this work is the use of supervised contrastive learning to enhance model generalization across different species and acoustic environments. Furthermore, we propose a novel supervised contrastive loss, inspired by prototypical networks, that reduces the computational complexity of the traditional supervised contrastive loss while maintaining performance. Additional contributions include leveraging metadata to improve generalization and tackling imbalanced multi-label classification. Although the primary application of this thesis is bioacoustic monitoring, the deep learning techniques developed are generalizable and can be applied to other audio domains, modalities, and applications
Dupuy, Eric. "Construction d’une notion scientifique et invariant : le cas d'élèves de l'enseignement primaire." Thesis, Bordeaux 2, 2009. http://www.theses.fr/2009BOR21652/document.
Full textThe purpose of this dissertation is to study how scientific conceptions are constructed in the course of experimental activities in physical sciences by young children at school. The study is based on three principal hypotheses: a) The formation of concepts and notions depends on invariant elements. b) The elaboration of thought results from personal reflections, actions and exchanges all anchored in a social dynamic process. c) Representations reveal and organise modes of thinking and their actualisation. In the first stage, the dissertation focuses on the formation of the notion of concept: from the evidencing of invariants to a stable conceptual architecture. Next, it presents the questions raised by the notion of learning and the expected achievement of the learner’s autonomy. Then, it develops a theory of representation, considering the question of the constitution and realisation of knowledge. In a second stage, the dissertation conducts its experimentations within the framework of an observation of classroom situations, the conversion of concrete situations into interpretable data being based on the phenomenological hypothesis from the point of view of constructivist epistemology. One situation refers to the theme of shade, the other to that of electricity: both evidence a complex process of cognitive elaboration, giving rise to conceptions based on a set of invariants. The representations thus reveal and structure the processes of thought. While « childish » items (R1) prove to be numerous, there also often emerge « rationalising » items (R2), either image-based or resting on internal dynamics. Finally, the dissertation demonstrates, in a still empirical way, how certain item combinations evince, so to speak before our very eyes, the child’s process of thinking in action — i.e. « enaction » in the Varela sense of the word
Diese Arbeit befasst sich mit der Konstruktion von wissenschaftlichen Konzepten im Verlauf von physikalischen Experimenten ,die Schüler im Unterricht durchführen. Sie stützt sich dabei auf drei Hypothesen. Die Bildung von Konzepten und Begriffen strukturiert sich um Invarianten. Die Erarbeitung eines Gedankens ergibt sich aus der Verbindung von eigenständigen Überlegungen, von Handlungen und von in sozialer Dynamik verankertem Austausch. Repräsentationen zeigen Modalitäten des Denkens und ihre Aktualisierung auf und organisieren sie. Diese Arbeit fokalisiert sich zunächst auf die Ausbildung des Konzeptbegriffs: vom Erfassen von Invarianten hin zu einer stabilen Konzeptarchitektur. Dann geht sie auf die Fragestellungen des Lernbegriffs ein und auf die Perspektive der Autonomie des Lernenden. Schließlich stellt sie die Repräsentationstheorie dar und fragt nach der Ausformung und der Offenkundigkeit der Erkenntnis. Im zweiten Teil dieser Arbeit werden die Experimente in Form von Beobachtungen in der Schule ausgewertet. Dabei beruht die Umwandlung von erlebten Situationen in verwertbare Daten auf der phänomenologischen Hypothese einer konstruktivistischen Epistemologie. Ein Experiment beschäftigt sich mit dem Schatten, das andere mit dem Thema Elektrizität. Sie belegen eine komplexe kognitive Erarbeitung, die zu Konzepten auf der Grundlage von Invarianten führen. Durch Repräsentationen werden die Gedankengänge offensichtlich und strukturiert. Auch wenn es zahlreich „kindliche“ Item (R1) gibt, werden „rationalisierende“ Item (von R2) oft mit Hilfe einer „bildgebenden“ Repräsentation (R1?R2) oder einer internen Dynamik (R2?R2) freigesetzt. Auf noch empirische Weise zeigt diese Arbeit schließlich wie gewisse Kombinationen von Item sozusagen unter unseren Augen die Entstehung des Gedanken beim Schüler aufzeigen: eine Enaction im Sinne von Varela
Esta tesis centra su objeto en el campo de la construcción de concepciones científicas en el curso de actividades experimentales en ciencias físicas conducidas en medio escolar por alumnos. Se apoya sobre tres hipótesis mayores. La formación de los conceptos y de nociones se estructura alrededor de elementos invariantes. La elaboración del pensamiento resulta de la conjunción de reflexiones, propias acciones e intercambios anclados en una dinámica social. Las representaciones descubren y organizan las modalidades de pensamiento y su actualización. En un primer tiempo la tesis se concentra en la formación de la noción de concepto: del reconocimiento de invariantes hacia una arquitectura conceptual estable. Luego expone las preguntas que plantea la noción de aprendizaje y la perspectiva de autonomía del novato. Luego presenta la teoría de la representación y plantea la cuestión de la constitución y la puesta en evidencia del conocimiento. En un segundo tiempo, la tesis inscribe sus experimentaciones en la observación de situaciones escolares basada la hipótesis fenomenológica en una epistemológica constructivista, la condición de la transformación de situaciones vividas en datos explotables. Una sobre el tema de la sombra, otra en lo de la electricidad, dan testimonio de una elaboración cognitiva compleja de donde nacen concepciones sobre la base de invariantes, las representaciones permiten descubrir y estructurar aproches de pensamiento. Si los “ítem” infantiles (R1) son numerosos, unos “ítem” “ racionalizantes (de R2) se desprenden a menudo llevados por una representación llena de imágenes (R1?R2), o en una dinámica interne (R2?R2). Por fin, la tesis muestra, de manera aun empÍrica, cómo ciertas combinaciones de ítem manifiestan, dicho sea asÍ “bajo nuestros ojos”, el pensamiento del alumno elaborándose: una “enacción” en el sentido de Varela
Badri, Hicham. "Sparse and Scale-Invariant Methods in Image Processing." Thesis, Bordeaux, 2015. http://www.theses.fr/2015BORD0139/document.
Full textIn this thesis, we present new techniques based on the notions of sparsity and scale invariance to design fast and efficient image processing applications. Instead of using the popular l1-norm to model sparsity, we focus on the use of non-convex penalties that promote more sparsity. We propose to use a first-order approximation to estimate a solution of non-convex proximal operators, which permits to easily use a wide rangeof penalties. We address also the problem of multi-sparsity, when the minimization problem is composed of various sparse terms, which typically arises in problems that require both a robust estimation to reject outliers and a sparse prior. These techniques are applied to various important problems in low-level computer vision such as edgeaware smoothing, image separation, robust integration and image deconvolution. We propose also to go beyond sparsity models and learn non-local spectral mapping with application to image denoising. Scale-invariance is another notion that plays an important role in our work. Using this principle, a precise definition of edges can be derived which can be complementary to sparsity. More precisely, we can extractinvariant features for classification from sparse representations in a deep convolutional framework. Scale-invariance permits also to extract relevant pixels for sparsifying images. We use this principle as well to improve optical ow estimation on turbulent images by imposing a sparse regularization on the local singular exponents instead of regular gradients
Dovgalecs, Vladislavs. "Indoor location estimation using a wearable camera with application to the monitoring of persons at home." Thesis, Bordeaux 1, 2011. http://www.theses.fr/2011BOR14384/document.
Full textVisual lifelog indexing by content has emerged as a high reward application. Enabled by the recent availability of miniaturized recording devices, the demand for automatic extraction of relevant information from wearable sensors generated content has grown. Among many other applications, indoor localization is one challenging problem to be addressed.Many standard solutions perform unreliably in indoors conditions or require significant intervention. In this thesis we address from the perspective of wearable video camera sensors using an image-based approach. The key contribution of this work is the development and the study of a location estimation system composed of diverse modules, which perform tasks ranging from low-level visual information extraction to final topological location estimation with the aid of automatic indexing algorithms. Within this framework, important contributions have been made by efficiently leveraging information brought by multiple visual features, unlabeled image data and the temporal continuity of the video.Early and late data fusion were considered, and shown to take advantage of the complementarities of multiple visual features describing the images. Due to the difficulty in obtaining annotated data in our context, semi-supervised approaches were investigated, to use unlabeled data as additional source of information, both for non-linear data-adaptive dimensionality reduction, and for improving classification. Herein we have developed a time-aware co-training approach that combines late data-fusion with the semi-supervised exploitation of both unlabeled data and time information. Finally, we have proposed to apply transformation invariant learning to adapt non-invariant descriptors to our localization framework.The methods have been tested on controlled publically available datasets to evaluate the gain of each contribution. This work has also been applied to the IMMED project, dealing with activity recognition and monitoring of the daily living using a wearable camera. In this context, the developed framework has been used to estimate localization on the real world IMMED project video corpus, which showed the potential of the approaches in such challenging conditions
Pouilly-Cathelain, Maxime. "Synthèse de correcteurs s’adaptant à des critères multiples de haut niveau par la commande prédictive et les réseaux de neurones." Electronic Thesis or Diss., université Paris-Saclay, 2020. http://www.theses.fr/2020UPASG019.
Full textThis PhD thesis deals with the control of nonlinear systems subject to nondifferentiable or nonconvex constraints. The objective is to design a control law considering any type of constraints that can be online evaluated.To achieve this goal, model predictive control has been used in addition to barrier functions included in the cost function. A gradient-free optimization algorithm has been used to solve this optimization problem. Besides, a cost function formulation has been proposed to ensure stability and robustness against disturbances for linear systems. The proof of stability is based on invariant sets and the Lyapunov theory.In the case of nonlinear systems, dynamic neural networks have been used as a predictor for model predictive control. Machine learning algorithms and the nonlinear observers required for the use of neural networks have been studied. Finally, our study has focused on improving neural network prediction in the presence of disturbances.The synthesis method presented in this work has been applied to obstacle avoidance by an autonomous vehicle
Bagheri-Crosson, Roja. "Mobilisation du concept de champ magnétique par des étudiants issus du DEUG "Sciences de la Matière" : analyse didactique à partir de la théorie des champs conceptuels." Toulouse 3, 2004. http://www.theses.fr/2004TOU30224.
Full text@Using the "theory of the conceptual fields" (Vergnaud, 1990), this research in didactics of physics science, reveals the dynamics of the cognitive patterns of undergraduate students (issus d'un DEUG "Sciences de la Matière"). The investigation consists in collecting data during "problem-solving situations" in electromagnetism, when students have to use the concept of magnetic field. After an exploratory study with the aim to identify the reccurent difficulties encountered by students when they mobilize concepts in electromagnetism, we sought to identify "operational invariants" and "schemes" used by students to solve these situations. The study shows that students : use "ready-to-use" invariants, invariants whose "signified in physics" are not specified and "not contextualized" invariants to the "problem-solving situations" ; use a very few "operational invariants" which belong to the university curriculum in electromagnetism ; meet enormous difficulties with the understanding of the concept of magnetic field and its relationship with the electric field in variable mode ; and operational invariants juxtaposed or combined without control of their relevance during the processes reasoning. .
Masquelier, Timothée. "Learning mechanisms to account for the speed, selectivity and invariance of responses in the visual cortex." Toulouse 3, 2008. http://thesesups.ups-tlse.fr/170/.
Full textIn this thesis I propose various activity-driven synaptic plasticity mechanisms that could account for the speed, selectivity and invariance of the neuronal responses in the visual cortex. Their biological plausibility is discussed. I also present the results of a relevant psychophysical experiment demonstrating that familiarity can accelerate visual processing. Beyond these results on the visual system, the studies presented here also credit the hypothesis that the brain uses the spike times to encode, decode, and process information - a theory referred to as 'temporal coding'. In such a framework the Spike Timing Dependent Plasticity may play a key role, by detecting repeating spike patterns and by generating faster and faster responses to those patterns
Vanleene, François. "Le role de l'anticipation dans l'apprentissage d'une langue seconde : etudes et applications didactiques pour l'enseignement du francais langue etrangere." Thesis, Nice, 2013. http://www.theses.fr/2013NICE2005.
Full textThis study intends to decrypt experimentally the interpreting process in the learning of a second language such as French, by questioning the traditional concept of analytical decoding and by substituting it the principle of anticipation. Our hypothesis is that utterances are not understood through a continuous and chronological adding of signs, but is rather constructed from invariant procedures of identification of the meaning and from the recognition of structures and universal schemes. The first chapter prepares the ground for this research by introducing three essential theories which could explain the phenomenon of anticipation: the theories of Universal Grammar (Chomsky), of Enunciative and Predicative Operations (Culioli) and of General Semantics (Pottier). We discuss the various prospects brought by these theories and we relate them with the topic of our research. In the second chapter, we present the iconographic material we have conducted our experiment with, the advantages of which consist in being neutral, syntactically adjustable andinterpretable in the subjects’ native tongue as much as in the target language. We introduce the Chinese participants and the principles of our experiment, which consists in converting oral utterances to iconographic sequences. We present the linguistic features of the sentences we have used by the aid of the theories we reviewed in the first section. In our third chapter, we make the analysis of the 14 subjects’ productions by taking account of the nature of the chosen icons, the order in which they are selected and their placement in the sequences. These three parameters allow us to reveal various schemes of anticipation and to confirm the theory according to which comprehension is a process of reconstruction from conceptual, cognitive and linguistic knowledge. The last chapter sums the experiment up, summarize our conclusions and test them against the theories about language universals and invariants. It defines also some possible threads that can be followed in the field of language acquisition and which consider the role of anticipation
Poulenard, Adrien. "Structures for deep learning and topology optimization of functions on 3D shapes." Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAX007.
Full textThe field of geometry processing is following a similar path as image analysis with the explosion of publications dedicated to deep learning in recent years. An important research effort is being made to reproduce the successes of deep learning 2D computer vision in the context of 3D shape analysis. Unlike images shapes comes in various representations like meshes or point clouds which often lack canonical structure. This makes traditional deep learning algorithms like Convolutional Neural Networks (CNN) non straightforward to apply to 3D data. In this thesis we propose three main contributions:First, we introduce a method to compare functions on different domains without correspondences and to deform them to make the topology of their set of levels more alike. We apply our method to the classical problem of shape matching in the context of functional maps to produce smoother and more accurate correspondences. Furthermore, our method is based on the continuous optimization of a differentiable energy with respect to the compared functions and is applicable to deep learning. We make two direct contributions to deep learning on 3D data. We introduce a new convolution operator over triangles meshes based on local polar coordinates and apply it to deep learning on meshes. Unlike previous works our operator takes all choices of polar coordinates into account without loss of directional information. Lastly we introduce a new rotation invariant convolution layer over point clouds and show that CNNs based on this layer can outperform state of the art methods in standard tasks on un-alligned datasets even with data augmentation
De, Witte Benjamin. "Étude des processus cognitifs impliqués dans la chirurgie minimalement invasive." Thesis, Lyon, 2018. http://www.theses.fr/2018LYSE1281/document.
Full textMinimally invasive surgery reduces postoperative pain, hospitalisation and associated costs. The use of long and rigid instruments in a closed haptic space limits incisions. The latter working conditions also challenge cognitive and motor skills of the surgeons. The surgeons need to mentally rotate the work scene, execute accurate movements with decreased sensitive and visual feedback. Moreover, the current learning paradigm needs to be updated to better match laparoscopic requirements. Our results show that cognitive features underpinning laparoscopy e.g., spatial abilities, hand eye coordination need to be contemplated to improve the learning curve. Simulators should provide the training of spatial abilities and better consider learning features (cognitive load, feedback). To be mastered and express the full potential of mental simulation, this technique should be implemented on a distributed way and earlier in the curricula. Hand-eye coordination needs explicit training outside the operation room. Finally, to favour skill learning, simulation techniques should be implemented on a complementary way in the curricula
Nisar, Zeeshan. "Self-supervised learning in the presence of limited labelled data for digital histopathology." Electronic Thesis or Diss., Strasbourg, 2024. http://www.theses.fr/2024STRAD016.
Full textA key challenge in applying deep learning to histopathology is the variation in stainings, both inter and intra-stain. Deep learning models trained on one stain (or domain) often fail on others, even for the same task (e.g., kidney glomeruli segmentation). Labelling each stain is expensive and time-consuming, prompting researchers to explore domain adaptation based stain-transfer methods. These aim to perform multi-stain segmentation using labels from only one stain but are limited by the introduction of domain shift, reducing performance. Detecting and quantifying this domain shift is important. This thesis focuses on unsupervised methods to develop a metric for detecting domain shift and proposes a novel stain-transfer approach to minimise it. While multi-stain algorithms reduce the need for labels in target stains, they may struggle with tissue types lacking source-stain labels. To address this, the thesis focuses to improve multi-stain segmentation with less reliance on labelled data using self-supervision. While this thesis focused on kidney glomeruli segmentation, the proposed methods are designed to be applicable to other histopathology tasks and domains, including medical imaging and computer vision
Zilber, Nicolas. "ERF and scale-free analyses of source-reconstructed MEG brain signals during a multisensory learning paradigm." Phd thesis, Université Paris Sud - Paris XI, 2014. http://tel.archives-ouvertes.fr/tel-00984990.
Full textMouawad, Pauline. "Modeling and predicting affect in audio signals : perspectives from acoustics and chaotic dynamics." Thesis, Bordeaux, 2017. http://www.theses.fr/2017BORD0627/document.
Full textThe present thesis describes a multidisciplinary research project on emotion recognition in sounds, covering psychological theories, acoustic-based signal analysis, machine learning and chaotic dynamics.In our social interactions and relationships, we rely greatly on the communication of information and on our perception of the messages transmitted. In fact communication happens when signals transmit information between a source and a destination. The signal can be verbal,and the information is then carried by sound patterns, such as words. In non verbal vocal communication however, information can be perceptual patterns that convey affective cues,that we sense and appraise in the form of intentions, attitudes, moods and emotions.The prevalence of the affective component can be seen in human computer interactions(HCI) where the development of automated applications that understand and express emotions has become crucial. Such systems need to be meaningful and friendly to the end user, so thatour interaction with them becomes a positive experience. Although the automatic recognition of emotions in sounds has received increased attention in recent years, it is still a young fieldof research. Not only does it contribute to Affective Computing in general, but it also provides insight into the significance of sounds in our daily life.In this thesis the problem of affect recognition is addressed from a dual perspective: we start by taking a standard approach of acoustic-based signal analysis, where we survey and experiment with existing features to determine their role in emotion communication. Then,we turn to chaotic dynamics and time series symbolization, to understand the role of the inherent dynamics of sounds in affective expressiveness. We conduct our studies in the context of nonverbal sounds, namely voice, music and environmental sounds.From a human listening point of view, an annotation task is conducted to build a ground truth of nonverbal singing voices, labelled with categorical descriptions of the two-dimensional model of affect. Two types of sounds are included in the study: vocal and glottal.From a psychological perspective, the present research addresses a debate that is of long standing among scientists and psychologists, concerning the common origins of music and voice.The question is addressed from an acoustic-based analysis as well as a nonlinear dynamics approach.From a modeling viewpoint, this work proposes a novel nonlinear dynamics approach for the recognition of affect in sound, based on chaotic dynamics and adaptive time series symbolization.Throughout this thesis, key contrasts in the expressiveness of affect are illustrated among the different types of sounds, through the analysis of acoustic properties, nonlinear dynamics metrics and predictions performances. Finally from a progressive perspective, we suggest that future works investigate features that are motivated by cognitive studies. We also suggest to examine to what extent our features reflect cognitive processes. Additionally we recommend that our dynamic features be tested inlarge scale ER studies through the participation in ER challenges, with an aim to verify if they gain consensus
Carrier, Pierre Luc. "Leveraging noisy side information for disentangling of factors of variation in a supervised setting." Thèse, 2014. http://hdl.handle.net/1866/11497.
Full textAlamian, Golnoush. "Investigation of neural activity in Schizophrenia during resting-state MEG : using non-linear dynamics and machine-learning to shed light on information disruption in the brain." Thesis, 2020. http://hdl.handle.net/1866/25254.
Full textPsychiatric disorders affect nearly a quarter of the world’s population. These typically bring about debilitating behavioural, functional and/or cognitive problems, for which the underlying neural mechanisms are poorly understood. These symptoms can significantly reduce the quality of life of affected individuals, impact those close to them, and bring on an economic burden on society. Hence, targeting the baseline neurophysiology associated with psychopathologies, by identifying more robust biomarkers, would improve the development of effective treatments. The first goal of this thesis is thus to contribute to a better characterization of neural dynamic alterations in mental health illnesses, specifically in schizophrenia and mood disorders. Accordingly, the first chapter of this thesis presents two systematic literature reviews, which investigate the resting-state changes in brain connectivity in schizophrenia, depression and bipolar disorder patients. Great strides have been made in neuroimaging research in identifying alterations in functional connectivity. However, these two reviews reveal a gap in the knowledge about the temporal basis of the neural mechanisms involved in the disruption of information integration in these pathologies, particularly in schizophrenia. Therefore, the second goal of this thesis is to characterize the baseline temporal neural alterations of schizophrenia. We present two studies for which we hypothesize that the resting temporal dysconnectivity could serve as a key biomarker in schizophrenia. These studies explore temporal integration deficits in schizophrenia by quantifying neural alterations of scale-free dynamics using resting-state magnetoencephalography (MEG) data. Specifically, we use (1) long-range temporal correlation (LRTC) analysis on oscillatory activity and (2) multifractal analysis on arrhythmic brain activity. In addition, we develop classification models (based on supervised machine-learning) to detect the cortical and sub-cortical features that allow for a robust division of patients and healthy controls. Given that these studies are based on MEG spontaneous brain activity, recorded at rest with either eyes-open or eyes-closed, we then explored the possibility of finding a distinctive feature that would combine both types of resting-state recordings. Thus, the third study investigates whether alterations in spectral amplitude between eyes-open and eyes-closed conditions can be used as a possible marker for schizophrenia. Overall, the three studies show changes in the scale-free dynamics of schizophrenia patients at rest that suggest a deterioration of the temporal processing of information in patients, which might relate to their cognitive and behavioural symptoms. The multimodal approach of this thesis, combining MEG, non-linear analyses and machine-learning, improves the characterization of the resting spatiotemporal neural organization of schizophrenia patients and healthy controls. Our findings provide new evidence for the temporal dysconnectivity hypothesis in schizophrenia. The results extend on previous studies by characterizing scale-free properties of deep brain structures and applying advanced non-linear metrics that are underused in the field of psychiatry. The results of this thesis contribute significantly to the identification of novel biomarkers in schizophrenia and show the importance of clarifying the temporal properties of altered intrinsic neural dynamics. Moreover, the presented studies offer a methodological framework that can be extended to other psychopathologies, such as depression.