Dissertationen zum Thema „Apprentissage profond – Apprentissage non supervisé (intelligence artificielle)“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Dissertationen für die Forschung zum Thema "Apprentissage profond – Apprentissage non supervisé (intelligence artificielle)" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Dissertationen für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
Boussik, Amine. „Apprentissage profond non-supervisé : Application à la détection de situations anormales dans l’environnement du train autonome“. Electronic Thesis or Diss., Valenciennes, Université Polytechnique Hauts-de-France, 2023. http://www.theses.fr/2023UPHF0040.
Der volle Inhalt der QuelleThe thesis addresses the challenges of monitoring the environment and detecting anomalies, especially obstacles, for an autonomous freight train. Although traditionally, rail transport was under human supervision, autonomous trains offer potential advantages in terms of costs, time, and safety. However, their operation in complex environments poses significant safety concerns. Instead of a supervised approach that requires costly and limited annotated data, this research adopts an unsupervised technique, using unlabeled data to detect anomalies based on methods capable of identifying atypical behaviors.Two environmental surveillance models are presented : the first, based on a convolutional autoencoder (CAE), is dedicated to identifying obstacles on the main track; the second, an advanced version incorporating the vision transformer (ViT), focuses on overall environmental surveillance. Both employ unsupervised learning techniques for anomaly detection.The results show that the highlighted method offers relevant insights for monitoring the environment of the autonomous freight train, holding potential to enhance its reliability and safety. The use of unsupervised techniques thus showcases the utility and relevance of their adoption in an application context for the autonomous train
Chen, Hao. „Vers la ré-identification de personnes non-supervisée“. Thesis, Université Côte d'Azur, 2022. http://www.theses.fr/2022COAZ4014.
Der volle Inhalt der QuelleAs a core component of intelligent video surveillance systems, person re-identification (ReID) targets at retrieving a person of interest across non-overlapping cameras. Despite significant improvements in supervised ReID, cumbersome annotation process makes it less scalable in real-world deployments. Moreover, as appearance representations can be affected by noisy factors, such as illumination level and camera properties, between different domains, person ReID models suffer a large performance drop in the presence of domain gaps. We are particularly interested in designing algorithms that can adapt a person ReID model to a target domain without human supervision. In such context, we mainly focus on designing unsupervised domain adaptation and unsupervised representation learning methods for person ReID.In this thesis, we first explore how to build robust representations by combining both global and local features under the supervised condition. Then, towards an unsupervised domain adaptive ReID system, we propose three unsupervised methods for person ReID, including 1) teacher-student knowledge distillation with asymmetric network structures for feature diversity encouragement, 2) joint generative and contrastive learning framework that generates augmented views with a generative adversarial network for contrastive learning, and 3) exploring inter-instance relations and designing relation-aware loss functions for better contrastive learning based person ReID.Our methods have been extensively evaluated on main-stream ReID datasets, such as Market-1501, DukeMTMC-reID and MSMT17. The proposed methods significantly outperform previous methods on the ReID datasets, significantly pushing person ReID to real-world deployments
Chareyre, Maxime. „Apprentissage non-supervisé pour la découverte de propriétés d'objets par découplage entre interaction et interprétation“. Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2023. http://www.theses.fr/2023UCFA0122.
Der volle Inhalt der QuelleRobots are increasingly used to achieve tasks in controlled environments. However, their use in open environments is still fraught with difficulties. Robotic agents are likely to encounter objects whose behaviour and function they are unaware of. In some cases, it must interact with these elements to carry out its mission by collecting or moving them, but without knowledge of their dynamic properties it is not possible to implement an effective strategy for resolving the mission.In this thesis, we present a method for teaching an autonomous robot a physical interaction strategy with unknown objects, without any a priori knowledge, the aim being to extract information about as many of the object's physical properties as possible from the interactions observed by its sensors. Existing methods for characterising objects through physical interactions do not fully satisfy these criteria. Indeed, the interactions established only provide an implicit representation of the object's dynamics, requiring supervision to identify their properties. Furthermore, the proposed solution is based on unrealistic scenarios without an agent. Our approach differs from the state of the art by proposing a generic method for learning interaction that is independent of the object and its properties, and can therefore be decoupled from the prediction phase. In particular, this leads to a completely unsupervised global pipeline.In the first phase, we propose to learn an interaction strategy with the object via an unsupervised reinforcement learning method, using an intrinsic motivation signal based on the idea of maximising variations in a state vector of the object. The aim is to obtain a set of interactions containing information that is highly correlated with the object's physical properties. This method has been tested on a simulated robot interacting by pushing and has enabled properties such as the object's mass, shape and friction to be accurately identified.In a second phase, we make the assumption that the true physical properties define a latent space that explains the object's behaviours and that this space can be identified from observations collected through the agent's interactions. We set up a self-supervised prediction task in which we adapt a state-of-the-art architecture to create this latent space. Our simulations confirm that combining the behavioural model with this architecture leads to the emergence of a representation of the object's properties whose principal components are shown to be strongly correlated with the object's physical properties.Once the properties of the objects have been extracted, the agent can use them to improve its efficiency in tasks involving these objects. We conclude this study by highlighting the performance gains achieved by the agent through training via reinforcement learning on a simplified object repositioning task where the properties are perfectly known.All the work carried out in simulation confirms the effectiveness of an innovative method aimed at autonomously discovering the physical properties of an object through the physical interactions of a robot. The prospects for extending this work involve transferring it to a real robot in a cluttered environment
Monnier, Tom. „Unsupervised image analysis by synthesis“. Electronic Thesis or Diss., Marne-la-vallée, ENPC, 2023. http://www.theses.fr/2023ENPC0037.
Der volle Inhalt der QuelleThe goal of this thesis is to develop machine learning approaches to analyze collections of images without annotations. Advances in this area hold particular promises for high-impact 3D-related applications (e.g., reconstructing a real-world scene with 3D actionable components for animation movies or video games) where annotating examples to teach the machines is difficult, as well as more micro applications related to specific needs (e.g., analyzing the character evolution from 12th century documents) where spending significant effort on annotating large-scale database is debatable. The central idea of this dissertation is to build machines that learn to analyze an image collection by synthesizing the images in the collection. Learning analysis models by synthesis is difficult because it requires the design of a learnable image generation system that explicitly exhibits the desired analysis output. To achieve our goal, we present three key contributions.The first contribution of this thesis is a new conceptual approach to category modeling. We propose to represent the category of an image, a 2D object or a 3D shape, with a prototype that is transformed using deep learning to model the different instances within the category. Specifically, we design meaningful parametric transformations (e.g., geometric deformations or colorimetric variations) and use neural networks to predict the transformation parameters necessary to instantiate the prototype for a given image. We demonstrate the effectiveness of this idea to cluster images and reconstruct 3D objects from single-view images. We obtain performances on par with the best state-of-the-art methods which leverage handcrafted features or annotations.The second contribution is a new way to discover elements in a collection of images. We propose to represent an image collection by a set of learnable elements composed together to synthesize the images and optimized by gradient descent. We first demonstrate the effectiveness of this idea by discovering 2D elements related to semantic objects represented by a large image collection. Our approach have performances similar to the best concurrent methods which synthesize images with neural networks, and ours comes with better interpretability. We also showcase the capability of this idea by discovering 3D elements related to simple primitive shapes given as input a collection of images depicting a scene from multiple viewpoints. Compared to prior works finding primitives in 3D point clouds, we showcase much better qualitative and quantitative performances.The third contribution is more technical and consist in a new formulation to compute differentiable mesh rendering. Specifically, we formulate the differentiable rendering of a 3D mesh as the alpha compositing of the mesh faces in an increasing depth order. Compared to prior works, this formulation is key to enable us to learn 3D meshes without requiring object region annotations. In addition, it allows us to seamlessly introduce the possibility to learn transparent meshes, which we design to model a scene as a composition of a variable number of meshes
Mehr, Éloi. „Unsupervised Learning of 3D Shape Spaces for 3D Modeling“. Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS566.
Der volle Inhalt der QuelleEven though 3D data is becoming increasingly more popular, especially with the democratization of virtual and augmented experiences, it remains very difficult to manipulate a 3D shape, even for designers or experts. Given a database containing 3D instances of one or several categories of objects, we want to learn the manifold of plausible shapes in order to develop new intelligent 3D modeling and editing tools. However, this manifold is often much more complex compared to the 2D domain. Indeed, 3D surfaces can be represented using various embeddings, and may also exhibit different alignments and topologies. In this thesis we study the manifold of plausible shapes in the light of the aforementioned challenges, by deepening three different points of view. First of all, we consider the manifold as a quotient space, in order to learn the shapes’ intrinsic geometry from a dataset where the 3D models are not co-aligned. Then, we assume that the manifold is disconnected, which leads to a new deep learning model that is able to automatically cluster and learn the shapes according to their typology. Finally, we study the conversion of an unstructured 3D input to an exact geometry, represented as a structured tree of continuous solid primitives
Loiseau, Romain. „Real-World 3D Data Analysis : Toward Efficiency and Interpretability“. Electronic Thesis or Diss., Marne-la-vallée, ENPC, 2023. http://www.theses.fr/2023ENPC0028.
Der volle Inhalt der QuelleThis thesis explores new deep-learning approaches for modeling and analyzing real-world 3D data. 3D data processing is helpful for numerous high-impact applications such as autonomous driving, territory management, industry facilities monitoring, forest inventory, and biomass measurement. However, annotating and analyzing 3D data can be demanding. Specifically, matching constraints regarding computing resources or annotation efficiency is often challenging. The difficulty of interpreting and understanding the inner workings of deep learning models can also limit their adoption.The computer vision community has made significant efforts to design methods to analyze 3D data, to perform tasks such as shape classification, scene segmentation, and scene decomposition. Early automated analysis relied on hand-crafted descriptors and incorporated prior knowledge about real-world acquisitions. Modern deep learning techniques demonstrate the best performances but are often computationally expensive, rely on large annotated datasets, and have low interpretability. In this thesis, we propose contributions that address these limitations.The first contribution of this thesis is an efficient deep-learning architecture for analyzing LiDAR sequences in real time. Our approach explicitly considers the acquisition geometry of rotating LiDAR sensors, which many autonomous driving perception pipelines use. Compared to previous work, which considers complete LiDAR rotations individually, our model processes the acquisition in smaller increments. Our proposed architecture achieves accuracy on par with the best methods while reducing processing time by more than five times and model size by more than fifty times.The second contribution is a deep learning method to summarize extensive 3D shape collections with a small set of 3D template shapes. We learn end-to-end a small number of 3D prototypical shapes that are aligned and deformed to reconstruct input point clouds. The main advantage of our approach is that its representations are in the 3D space and can be viewed and manipulated. They constitute a compact and interpretable representation of 3D shape collections and facilitate annotation, leading to emph{state-of-the-art} results for few-shot semantic segmentation.The third contribution further expands unsupervised analysis for parsing large real-world 3D scans into interpretable parts. We introduce a probabilistic reconstruction model to decompose an input 3D point cloud using a small set of learned prototypical shapes. Our network determines the number of prototypes to use to reconstruct each scene. We outperform emph{state-of-the-art} unsupervised methods in terms of decomposition accuracy while remaining visually interpretable. We offer significant advantages over existing approaches as our model does not require manual annotations.This thesis also introduces two open-access annotated real-world datasets, HelixNet and the Earth Parser Dataset, acquired with terrestrial and aerial LiDARs, respectively. HelixNet is the largest LiDAR autonomous driving dataset with dense annotations and provides point-level sensor metadata crucial for precisely measuring the latency of semantic segmentation methods. The Earth Parser Dataset consists of seven aerial LiDAR scenes, which can be used to evaluate 3D processing techniques' performances in diverse environments.We hope that these datasets and reliable methods considering the specificities of real-world acquisitions will encourage further research toward more efficient and interpretable models
Manenti, Céline. „Découverte d'unités linguistiques à l'aide de méthodes d'apprentissage non supervisé“. Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30074.
Der volle Inhalt der QuelleThe discovery of elementary linguistic units (phonemes, words) only from sound recordings is an unresolved problem that arouses a strong interest from the community of automatic speech processing, as evidenced by the many recent contributions of the state of the art. During this thesis, we focused on using neural networks to answer the problem. We approached the problem using neural networks in a supervised, poorly supervised and multilingual manner. We have developed automatic phoneme segmentation and phonetic classification tools based on convolutional neural networks. The automatic segmentation tool obtained 79% F-measure on the BUCKEYE conversational speech corpus. This result is similar to a human annotator according to the inter-annotator agreement provided by the creators of the corpus. In addition, it does not need a lot of data (about ten minutes per speaker and 5 different speakers) to be effective. In addition, it is portable to other languages (especially for poorly endowed languages such as xitsonga). The phonetic classification system makes it possible to set the various parameters and hyperparameters that are useful for an unsupervised scenario. In the unsupervised context, the neural networks (Auto-Encoders) allowed us to generate new parametric representations, concentrating the information of the input frame and its neighboring frames. We studied their utility for audio compression from the raw signal, for which they were effective (low RMS, even at 99% compression). We also carried out an innovative pre-study on a different use of neural networks, to generate vectors of parameters not from the outputs of the layers but from the values of the weights of the layers. These parameters are designed to mimic Linear Predictive Coefficients (LPC). In the context of the unsupervised discovery of phoneme-like units (called pseudo-phones in this memory) and the generation of new phonetically discriminative parametric representations, we have coupled a neural network with a clustering tool (k-means ). The iterative alternation of these two tools allowed the generation of phonetically discriminating parameters for the same speaker: low rates of intra-speaker ABx error of 7.3% for English, 8.5% for French and 8 , 4% for Mandarin were obtained. These results allow an absolute gain of about 4% compared to the baseline (conventional parameters MFCC) and are close to the best current approaches (1% more than the winner of the Zero Resource Speech Challenge 2017). The inter-speaker results vary between 12% and 15% depending on the language, compared to 21% to 25% for MFCCs
Debard, Quentin. „Automatic learning of next generation human-computer interactions“. Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEI036.
Der volle Inhalt der QuelleArtificial Intelligence (AI) and Human-Computer Interactions (HCIs) are two research fields with relatively few common work. HCI specialists usually design the way we interact with devices directly from observations and measures of human feedback, manually optimizing the user interface to better fit users’ expectations. This process is hard to optimize: ergonomy, intuitivity and ease of use are key features in a User Interface (UI) that are too complex to be simply modelled from interaction data. This drastically restrains the possible uses of Machine Learning (ML) in this design process. Currently, ML in HCI is mostly applied to gesture recognition and automatic display, e.g. advertisement or item suggestion. It is also used to fine tune an existing UI to better optimize it, but as of now it does not participate in designing new ways to interact with computers. Our main focus in this thesis is to use ML to develop new design strategies for overall better UIs. We want to use ML to build intelligent – understand precise, intuitive and adaptive – user interfaces using minimal handcrafting. We propose a novel approach to UI design: instead of letting the user adapt to the interface, we want the interface and the user to adapt mutually to each other. The goal is to reduce human bias in protocol definition while building co-adaptive interfaces able to further fit individual preferences. In order to do so, we will put to use the different mechanisms available in ML to automatically learn behaviors, build representations and take decisions. We will be experimenting on touch interfaces, as these interfaces are vastly used and can provide easily interpretable problems. The very first part of our work will focus on processing touch data and use supervised learning to build accurate classifiers of touch gestures. The second part will detail how Reinforcement Learning (RL) can be used to model and learn interaction protocols given user actions. Lastly, we will combine these RL models with unsupervised learning to build a setup allowing for the design of new interaction protocols without the need for real user data
Shahid, Mustafizur Rahman. „Deep learning for Internet of Things (IoT) network security“. Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAS003.
Der volle Inhalt der QuelleThe growing Internet of Things (IoT) introduces new security challenges for network activity monitoring. Most IoT devices are vulnerable because of a lack of security awareness from device manufacturers and end users. As a consequence, they have become prime targets for malware developers who want to turn them into bots. Contrary to general-purpose devices, an IoT device is designed to perform very specific tasks. Hence, its networking behavior is very stable and predictable making it well suited for data analysis techniques. Therefore, the first part of this thesis focuses on leveraging recent advances in the field of deep learning to develop network monitoring tools for the IoT. Two types of network monitoring tools are explored: IoT device type recognition systems and IoT network Intrusion Detection Systems (NIDS). For IoT device type recognition, supervised machine learning algorithms are trained to perform network traffic classification and determine what IoT device the traffic belongs to. The IoT NIDS consists of a set of autoencoders, each trained for a different IoT device type. The autoencoders learn the legitimate networking behavior profile and detect any deviation from it. Experiments using network traffic data produced by a smart home show that the proposed models achieve high performance.Despite yielding promising results, training and testing machine learning based network monitoring systems requires tremendous amount of IoT network traffic data. But, very few IoT network traffic datasets are publicly available. Physically operating thousands of real IoT devices can be very costly and can rise privacy concerns. In the second part of this thesis, we propose to leverage Generative Adversarial Networks (GAN) to generate bidirectional flows that look like they were produced by a real IoT device. A bidirectional flow consists of the sequence of the sizes of individual packets along with a duration. Hence, in addition to generating packet-level features which are the sizes of individual packets, our developed generator implicitly learns to comply with flow-level characteristics, such as the total number of packets and bytes in a bidirectional flow or the total duration of the flow. Experimental results using data produced by a smart speaker show that our method allows us to generate high quality and realistic looking synthetic bidirectional flows
Hamis, Sébastien. „Compression de contenus visuels pour transmission mobile sur réseaux de très bas débit“. Electronic Thesis or Diss., Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAS020.
Der volle Inhalt der QuelleThe field of visual content compression (image, video, 2D/3D graphics elements) has known spectacular achievements for more than twenty years, with the emergence numerous international standards such as JPEG, JPEG2000 for still image compression, or MPEG-1/2/4 for video and 3D graphics content coding.The apparition of smartphones and of their related applications have also benefited from these advances, the image being today ubiquitous in a context of mobility. Nevertheless, image transmission requires reliable and available networks, since such visual data that are inherently bandwidth-intensive. While developed countries benefit today from high-performance mobile networks (3G, 4G...), this is not the case in a certain number of regions of the world, particularly in emerging countries, where communications still rely on 2G SMS networks. Transmitting visual content in such a context becomes a highly ambitious challenge, requiring the elaboration of new, for very low bitrate compression algorithm. The challenge is to ensure images transmission over a narrow bandwidth corresponding to a relatively small set (10 to 20) of SMS (140 bytes per SMS).To meet such constraints, multiple axes of development have been considered. After a state-of-the-art of traditional image compression techniques, we have oriented our research towards deep learning methods, aiming achieve post-treatments over strongly compressed data in order to improve the quality of the decoded content.Our contributions are structures around the creation of a new compression scheme, including existing codecs and a panel of post-processing bricks aiming at enhancing highly compressed content. Such bricks represent dedicated deep neural networks, which perform super-resolution and/or compression artifact reduction operations, specifically trained to meet the targeted objectives. These operations are carried out on the decoder side and can be interpreted as image reconstruction algorithms from heavily compressed versions. This approach offers the advantage of being able to rely on existing codecs, which are particularly light and resource-efficient. In our work, we have retained the BPG format, which represents the state of art in the field, but other compression schemes can also be considered.Regarding the type of neural networks, we have adopted Generative Adversarials Nets-GAN, which are particularly well-suited for objectives of reconstruction from incomplete data. Specifically, the two architectures retained and adapted to our objectives are the SRGAN and ESRGAN networks. The impact of the various elements and parameters involved, such as the super-resolution factors and the loss functions, are analyzed in detail.A final contribution concerns experimental evaluation performed. After showing the limitations of objective metrics, which fail to take into account the visual quality of the image, we have put in place a subjective evaluation protocol. The results obtained in terms of MOS (Mean Opinion Score) fully demonstrate the relevance of the proposed reconstruction approaches.Finally, we open our work to different use cases, of a more general nature. This is particularly the case for high-resolution image processing and for video compression
Chafik, Sanaa. „Machine learning techniques for content-based information retrieval“. Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLL008/document.
Der volle Inhalt der QuelleThe amount of media data is growing at high speed with the fast growth of Internet and media resources. Performing an efficient similarity (nearest neighbor) search in such a large collection of data is a very challenging problem that the scientific community has been attempting to tackle. One of the most promising solutions to this fundamental problem is Content-Based Media Retrieval (CBMR) systems. The latter are search systems that perform the retrieval task in large media databases based on the content of the data. CBMR systems consist essentially of three major units, a Data Representation unit for feature representation learning, a Multidimensional Indexing unit for structuring the resulting feature space, and a Nearest Neighbor Search unit to perform efficient search. Media data (i.e. image, text, audio, video, etc.) can be represented by meaningful numeric information (i.e. multidimensional vector), called Feature Description, describing the overall content of the input data. The task of the second unit is to structure the resulting feature descriptor space into an index structure, where the third unit, effective nearest neighbor search, is performed.In this work, we address the problem of nearest neighbor search by proposing three Content-Based Media Retrieval approaches. Our three approaches are unsupervised, and thus can adapt to both labeled and unlabeled real-world datasets. They are based on a hashing indexing scheme to perform effective high dimensional nearest neighbor search. Unlike most recent existing hashing approaches, which favor indexing in Hamming space, our proposed methods provide index structures adapted to a real-space mapping. Although Hamming-based hashing methods achieve good accuracy-speed tradeoff, their accuracy drops owing to information loss during the binarization process. By contrast, real-space hashing approaches provide a more accurate approximation in the mapped real-space as they avoid the hard binary approximations.Our proposed approaches can be classified into shallow and deep approaches. In the former category, we propose two shallow hashing-based approaches namely, "Symmetries of the Cube Locality Sensitive Hashing" (SC-LSH) and "Cluster-based Data Oriented Hashing" (CDOH), based respectively on randomized-hashing and shallow learning-to-hash schemes. The SC-LSH method provides a solution to the space storage problem faced by most randomized-based hashing approaches. It consists of a semi-random scheme reducing partially the randomness effect of randomized hashing approaches, and thus the memory storage problem, while maintaining their efficiency in structuring heterogeneous spaces. The CDOH approach proposes to eliminate the randomness effect by combining machine learning techniques with the hashing concept. The CDOH outperforms the randomized hashing approaches in terms of computation time, memory space and search accuracy.The third approach is a deep learning-based hashing scheme, named "Unsupervised Deep Neuron-per-Neuron Hashing" (UDN2H). The UDN2H approach proposes to index individually the output of each neuron of the top layer of a deep unsupervised model, namely a Deep Autoencoder, with the aim of capturing the high level individual structure of each neuron output.Our three approaches, SC-LSH, CDOH and UDN2H, were proposed sequentially as the thesis was progressing, with an increasing level of complexity in terms of the developed models, and in terms of the effectiveness and the performances obtained on large real-world datasets
Dekhtiar, Jonathan. „Deep Learning and unsupervised learning to automate visual inspection in the manufacturing industry“. Thesis, Compiègne, 2019. http://www.theses.fr/2019COMP2513.
Der volle Inhalt der QuelleAlthough studied since 1970, automatic visual inspection on production lines still struggles to be applied on a large scale and at low cost. The methods used depend greatly on the availability of domain experts. This inevitably leads to increased costs and reduced flexibility in the methods used. Since 2012, advances in the field of Deep Learning have enabled many advances in this direction, particularly thanks to convolutional neura networks that have achieved near-human performance in many areas associated with visual perception (e.g. object recognition and detection, etc.). This thesis proposes an unsupervised approach to meet the needs of automatic visual inspection. This method, called AnoAEGAN, combines adversarial learning and the estimation of a probability density function. These two complementary approaches make it possible to jointly estimate the pixel-by-pixel probability of a visual defect on an image. The model is trained from a very limited number of images (i.e. less than 1000 images) without using expert knowledge to "label" the data beforehand. This method allows increased flexibility with a limited training time and therefore great versatility, demonstrated on ten different tasks without any modification of the model. This method should reduce development costs and the time required to deploy in production. This method can also be deployed in a complementary way to a supervised approach in order to benefit from the advantages of each approach
Bilodeau, Anthony. „Apprentissage faiblement supervisé appliqué à la segmentation d'images de protéines neuronales“. Master's thesis, Université Laval, 2020. http://hdl.handle.net/20.500.11794/39752.
Der volle Inhalt der QuelleThèse ou mémoire avec insertion d'articles
Tableau d'honneur de la Faculté des études supérieures et postdoctorales, 2020-2021
En biologie cellulaire, la microscopie optique est couramment utilisée pour visualiser et caractériser la présence et la morphologie des structures biologiques. Suite à l’acquisition, un expert devra effectuer l’annotation des structures pour quantification. Cette tâche est ardue, requiert de nombreuses heures de travail, parfois répétitif, qui peut résulter en erreurs d’annotations causées par la fatigue d’étiquetage. L’apprentissage machine promet l’automatisation de tâches complexes à partir d’un grand lot de données exemples annotés. Mon projet de maîtrise propose d’utiliser des techniques faiblement supervisées, où les annotations requises pour l’entraînement sont réduites et/ou moins précises, pour la segmentation de structures neuronales. J’ai d’abord testé l’utilisation de polygones délimitant la structure d’intérêt pour la tâche complexe de segmentation de la protéine neuronale F-actine dans des images de microscopie à super-résolution. La complexité de la tâche est supportée par la morphologie hétérogène des neurones, le nombre élevé d’instances à segmenter dans une image et la présence de nombreux distracteurs. Malgré ces difficultés, l’utilisation d’annotations faibles a permis de quantifier un changement novateur de la conformation de la protéine F-actine en fonction de l’activité neuronale. J’ai simplifié davantage la tâche d’annotation en requérant seulement des étiquettes binaires renseignant sur la présence des structures dans l’image réduisant d’un facteur 30 le temps d’annotation. De cette façon, l’algorithme est entraîné à prédire le contenu d’une image et extrait ensuite les caractéristiques sémantiques importantes pour la reconnaissance de la structure d’intérêt à l’aide de mécanismes d’attention. La précision de segmentation obtenue sur les images de F-actine est supérieure à celle des annotations polygonales et équivalente à celle des annotations précises d’un expert. Cette nouvelle approche devrait faciliter la quantification des changements dynamiques qui se produisent sous le microscope dans des cellules vivantes et réduire les erreurs causées par l’inattention ou le biais de sélection des régions d’intérêt dans les images de microscopie.
In cell biology, optical microscopy is commonly used to visualize and characterize the presenceand morphology of biological structures. Following the acquisition, an expert will have toannotate the structures for quantification. This is a difficult task, requiring many hours ofwork, sometimes repetitive, which can result in annotation errors caused by labelling fatigue.Machine learning promises to automate complex tasks from a large set of annotated sampledata. My master’s project consists of using weakly supervised techniques, where the anno-tations required for training are reduced and/or less precise, for the segmentation of neuralstructures.I first tested the use of polygons delimiting the structure of interest for the complex taskof segmentation of the neuronal protein F-actin in super-resolution microscopy images. Thecomplexity of the task is supported by the heterogeneous morphology of neurons, the highnumber of instances to segment in an image and the presence of many distractors. Despitethese difficulties, the use of weak annotations has made it possible to quantify an innovativechange in the conformation of the F-actin protein as a function of neuronal activity. I furthersimplified the annotation task by requiring only binary labels that indicate the presence ofstructures in the image, reducing annotation time by a factor of 30. In this way, the algorithmis trained to predict the content of an image and then extract the semantic characteristicsimportant for recognizing the structure of interest using attention mechanisms. The segmen-tation accuracy obtained on F-actin images is higher than that of polygonal annotations andequivalent to that of an expert’s precise annotations. This new approach should facilitate thequantification of dynamic changes that occur under the microscope in living cells and reduceerrors caused by inattention or bias in the selection of regions of interest in microscopy images.
Yin, Hao. „Étude des réseaux de neurones en mode non supervisé : application à la reconnaissance des formes“. Compiègne, 1992. http://www.theses.fr/1992COMPD524.
Der volle Inhalt der QuelleTamaazousti, Youssef. „Vers l’universalité des représentations visuelle et multimodales“. Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC038/document.
Der volle Inhalt der QuelleBecause 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
Frery, Jordan. „Ensemble Learning for Extremely Imbalced Data Flows“. Thesis, Lyon, 2019. http://www.theses.fr/2019LYSES034.
Der volle Inhalt der QuelleMachine learning is the study of designing algorithms that learn from trainingdata to achieve a specific task. The resulting model is then used to predict overnew (unseen) data points without any outside help. This data can be of manyforms such as images (matrix of pixels), signals (sounds,...), transactions (age,amount, merchant,...), logs (time, alerts, ...). Datasets may be defined to addressa specific task such as object recognition, voice identification, anomaly detection,etc. In these tasks, the knowledge of the expected outputs encourages a supervisedlearning approach where every single observed data is assigned to a label thatdefines what the model predictions should be. For example, in object recognition,an image could be associated with the label "car" which suggests that the learningalgorithm has to learn that a car is contained in this picture, somewhere. This is incontrast with unsupervised learning where the task at hand does not have explicitlabels. For example, one popular topic in unsupervised learning is to discoverunderlying structures contained in visual data (images) such as geometric formsof objects, lines, depth, before learning a specific task. This kind of learning isobviously much harder as there might be potentially an infinite number of conceptsto grasp in the data. In this thesis, we focus on a specific scenario of thesupervised learning setting: 1) the label of interest is under represented (e.g.anomalies) and 2) the dataset increases with time as we receive data from real-lifeevents (e.g. credit card transactions). In fact, these settings are very common inthe industrial domain in which this thesis takes place
Durand, Thibaut. „Weakly supervised learning for visual recognition“. Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066142/document.
Der volle Inhalt der QuelleThis thesis studies the problem of classification of images, where the goal is to predict if a semantic category is present in the image, based on its visual content. To analyze complex scenes, it is important to learn localized representations. To limit the cost of annotation during training, we have focused on weakly supervised learning approaches. In this thesis, we propose several models that simultaneously classify and localize objects, using only global labels during training. The weak supervision significantly reduces the cost of full annotation, but it makes learning more challenging. The key issue is how to aggregate local scores - e.g. regions - into global score - e.g. image. The main contribution of this thesis is the design of new pooling functions for weakly supervised learning. In particular, we propose a “max + min” pooling function, which unifies many pooling functions. We describe how to use this pooling in the Latent Structured SVM framework as well as in convolutional networks. To solve the optimization problems, we present several solvers, some of which allow to optimize a ranking metric such as Average Precision. We experimentally show the interest of our models with respect to state-of-the-art methods, on ten standard image classification datasets, including the large-scale dataset ImageNet
Sarazin, Tugdual. „Apprentissage massivement distribué dans un environnement Big Data“. Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD050.
Der volle Inhalt der QuelleIn recent years, the amount of data analysed by companies and research laboratories increased strongly, opening the era of BigData. However, these raw data are frequently non-categorized and uneasy to use. This thesis aims to improve and ease the pre-treatment and comprehension of these big amount of data by using unsupervised machine learning algorithms.The first part of this thesis is dedicated to a state-of-the-art of clustering and biclustering algorithms and to an introduction to big data technologies. The first part introduces the conception of clustering Self-Organizing Map algorithm [Kohonen,2001] in big data environment. Our algorithm (SOM-MR) provides the same advantages as the original algorithm, namely the creation of data visualisation map based on data clusters. Moreover, it uses the Spark platform that makes it able to treat a big amount of data in a short time. Thanks to the popularity of this platform, it easily fits in many data mining environments. This is what we demonstrated it in our project \Square Predict" carried out in partnership with Axa insurance. The aim of this project was to provide a real-time data analysing platform in order to estimate the severity of natural disasters or improve residential risks knowledge. Throughout this project, we proved the efficiency of our algorithm through its capacity to analyse and create visualisation out of a big volume of data coming from social networks and open data.The second part of this work is dedicated to a new bi-clustering algorithm. BiClustering consists in making a cluster of observations and variables at the same time. In this contribution we put forward a new approach of bi-clustering based on the self-organizing maps algorithm that can scale on big amounts of data (BiTM-MR). To reach this goal, this algorithm is also based on a the Spark platform. It brings out more information than the SOM-MR algorithm because besides producing observation groups, it also associates variables to these groups,thus creating bi-clusters of variables and observations
Thépaut, Solène. „Problèmes de clustering liés à la synchronie en écologie : estimation de rang effectif et détection de ruptures sur les arbres“. Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS477/document.
Der volle Inhalt der QuelleIn the view of actual global changes widely caused by human activities, it becomes urgent to understand the drivers of communities' stability. Synchrony between time series of abundances is one of the most important mechanisms. This thesis offers three different angles in order to answer different questions linked to interspecific and spatial synchrony. The works presented find applications beyond the ecological frame. A first chapter is dedicated to the estimation of effective rank of matrices in ℝ or ℂ. We offer tools allowing to measure the synchronisation rate of observations matrices. In the second chapter, we base on the existing work on change-points detection problem on chains in order to offer algorithms which detects change-points on trees. The methods can be used with most data that have to be represented as a tree. In order to study the link between interspecific synchrony and long term tendencies or traits of butterflies species, we offer in the last chapter adaptation of clustering and supervised machine learning methods, such as Random Forest or Artificial Neural Networks to ecological data
Ghesmoune, Mohammed. „Apprentissage non supervisé de flux de données massives : application aux Big Data d'assurance“. Thesis, Sorbonne Paris Cité, 2016. http://www.theses.fr/2016USPCD061/document.
Der volle Inhalt der QuelleThe research outlined in this thesis concerns the development of approaches based on growing neural gas (GNG) for clustering of data streams. We propose three algorithmic extensions of the GNG approaches: sequential, distributed and parallel, and hierarchical; as well as a model for scalability using MapReduce and its application to learn clusters from the real insurance Big Data in the form of a data stream. We firstly propose the G-Stream method. G-Stream, as a “sequential" clustering method, is a one-pass data stream clustering algorithm that allows us to discover clusters of arbitrary shapes without any assumptions on the number of clusters. G-Stream uses an exponential fading function to reduce the impact of old data whose relevance diminishes over time. The links between the nodes are also weighted. A reservoir is used to hold temporarily the distant observations in order to reduce the movements of the nearest nodes to the observations. The batchStream algorithm is a micro-batch based method for clustering data streams which defines a new cost function taking into account that subsets of observations arrive in discrete batches. The minimization of this function, which leads to a topological clustering, is carried out using dynamic clusters in two steps: an assignment step which assigns each observation to a cluster, followed by an optimization step which computes the prototype for each node. A scalable model using MapReduce is then proposed. It consists of decomposing the data stream clustering problem into the elementary functions, Map and Reduce. The observations received in each sub-dataset (within a time interval) are processed through deterministic parallel operations (Map and Reduce) to produce the intermediate states or the final clusters. The batchStream algorithm is validated on the insurance Big Data. A predictive and analysis system is proposed by combining the clustering results of batchStream with decision trees. The architecture and these different modules from the computational core of our Big Data project, called Square Predict. GH-Stream for both visualization and clustering tasks is our third extension. The presented approach uses a hierarchical and topological structure for both of these tasks
Abou, Bakr Nachwa. „Reconnaissance et modélisation des actions de manipulation“. Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM010.
Der volle Inhalt der QuelleThis thesis addresses the problem of recognition, modelling and description of human activities. We describe results on three problems: (1) the use of transfer learning for simultaneous visual recognition of objects and object states, (2) the recognition of manipulation actions from state transitions, and (3) the interpretation of a series of actions and states as events in a predefined story to construct a narrative description.These results have been developed using food preparation activities as an experimental domain. We start by recognising food classes such as tomatoes and lettuce and food states, such as sliced and diced, during meal preparation. We adapt the VGG network architecture to jointly learn the representations of food items and food states using transfer learning. We model actions as the transformation of object states. We use recognised object properties (state and type) to detect corresponding manipulation actions by tracking object transformations in the video. Experimental performance evaluation for this approach is provided using the 50 salads and EPIC-Kitchen datasets. We use the resulting action descriptions to construct narrative descriptions for complex activities observed in videos of 50 salads dataset
Peyrache, Jean-Philippe. „Nouvelles approches itératives avec garanties théoriques pour l'adaptation de domaine non supervisée“. Thesis, Saint-Etienne, 2014. http://www.theses.fr/2014STET4023/document.
Der volle Inhalt der QuelleDuring the past few years, an increasing interest for Machine Learning has been encountered, in various domains like image recognition or medical data analysis. However, a limitation of the classical PAC framework has recently been highlighted. It led to the emergence of a new research axis: Domain Adaptation (DA), in which learning data are considered as coming from a distribution (the source one) different from the one (the target one) from which are generated test data. The first theoretical works concluded that a good performance on the target domain can be obtained by minimizing in the same time the source error and a divergence term between the two distributions. Three main categories of approaches are derived from this idea : by reweighting, by reprojection and by self-labeling. In this thesis work, we propose two contributions. The first one is a reprojection approach based on boosting theory and designed for numerical data. It offers interesting theoretical guarantees and also seems able to obtain good generalization performances. Our second contribution consists first in a framework filling the gap of the lack of theoretical results for self-labeling methods by introducing necessary conditions ensuring the good behavior of this kind of algorithm. On the other hand, we propose in this framework a new approach, using the theory of (epsilon, gamma, tau)- good similarity functions to go around the limitations due to the use of kernel theory in the specific context of structured data
Allesiardo, Robin. „Bandits Manchots sur Flux de Données Non Stationnaires“. Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLS334/document.
Der volle Inhalt der QuelleThe multi-armed bandit is a framework allowing the study of the trade-off between exploration and exploitation under partial feedback. At each turn t Є [1,T] of the game, a player has to choose an arm kt in a set of K and receives a reward ykt drawn from a reward distribution D(µkt) of mean µkt and support [0,1]. This is a challeging problem as the player only knows the reward associated with the played arm and does not know what would be the reward if she had played another arm. Before each play, she is confronted to the dilemma between exploration and exploitation; exploring allows to increase the confidence of the reward estimators and exploiting allows to increase the cumulative reward by playing the empirical best arm (under the assumption that the empirical best arm is indeed the actual best arm).In the first part of the thesis, we will tackle the multi-armed bandit problem when reward distributions are non-stationary. Firstly, we will study the case where, even if reward distributions change during the game, the best arm stays the same. Secondly, we will study the case where the best arm changes during the game. The second part of the thesis tacles the contextual bandit problem where means of reward distributions are now dependent of the environment's current state. We will study the use of neural networks and random forests in the case of contextual bandits. We will then propose meta-bandit based approach for selecting online the most performant expert during its learning
Liu, Jingshu. „Unsupervised cross-lingual representation modeling for variable length phrases“. Thesis, Nantes, 2020. http://www.theses.fr/2020NANT4009.
Der volle Inhalt der QuelleSignificant advances have been achieved in bilingual word-level alignment from comparable corpora, yet the challenge remains for phrase-level alignment. Traditional methods to phrase alignment can only handle phrase of equal length, while word embedding based approaches learn phrase embeddings as individual vocabulary entries suffer from the data sparsity and cannot handle out of vocabulary phrases. Since bilingual alignment is a vector comparison task, phrase representation plays a key role. In this thesis, we study the approaches for unified phrase modeling and cross-lingual phrase alignment, ranging from co-occurrence models to most recent neural state-of-the-art approaches. We review supervised and unsupervised frameworks for modeling cross-lingual phrase representations. Two contributions are proposed in this work. First, a new architecture called tree-free recursive neural network (TF-RNN) for modeling phrases of variable length which, combined with a wrapped context prediction training objective, outperforms the state-of-the-art approaches on monolingual phrase synonymy task with only plain text training data. Second, for cross-lingual modeling, we propose to incorporate an architecture derived from TF-RNN in an encoder-decoder model with a pseudo back translation mechanism inspired by unsupervised neural machine translation. Our proposition improves significantly bilingual alignment of different length phrases
Gal, Jocelyn. „Application d’algorithmes de machine learning pour l’exploitation de données omiques en oncologie“. Electronic Thesis or Diss., Université Côte d'Azur (ComUE), 2019. http://theses.univ-cotedazur.fr/2019AZUR6026.
Der volle Inhalt der QuelleThe development of computer science in medicine and biology has generated a large volume of data. The complexity and the amount of information to be integrated for optimal decision-making in medicine have largely exceeded human capacities. These data includes demographic, clinical and radiological variables, but also biological variables and particularly omics (genomics, proteomics, transcriptomics and metabolomics) characterized by a large number of measured variables relatively to a generally small number of patients. Their analysis represents a real challenge as they are frequently "noisy" and associated with situations of multi-colinearity. Nowadays, computational power makes it possible to identify clinically relevant models within these sets of data by using machine learning algorithms. Through this thesis, our goal is to apply supervised and unsupervised learning methods, to large biological data, in order to participate in the optimization of the classification and therapeutic management of patients with various types of cancer. In the first part of this work a supervised learning method is applied to germline immunogenetic data to predict the efficacy and toxicity of immune checkpoint inhibitor therapy. In the second part, different unsupervised learning methods are compared to evaluate the contribution of metabolomics in the diagnosis and management of breast cancer. Finally, the third part of this work aims to expose the contribution that simulated therapeutic trials can make in biomedical research. The application of machine learning methods in oncology offers new perspectives to clinicians allowing them to make diagnostics faster and more accurately, or to optimize therapeutic management in terms of efficacy and toxicity
Cherfi, Zohra Leila. „Diagnostic de systèmes complexes en contextes non supervisé et partiellement supervisé : application au circuit de voie ferroviaire“. Phd thesis, UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE, 2011. http://tel.archives-ouvertes.fr/tel-01006538.
Der volle Inhalt der QuelleOthmani-Guibourg, Mehdi. „Supervised learning for distribution of centralised multiagent patrolling strategies“. Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS534.
Der volle Inhalt der QuelleFor nearly two decades, patrolling has received significant attention from the multiagent community. Multiagent patrolling (MAP) consists in modelling a patrol task to optimise as a multiagent system. The problem of optimising a patrol task is to distribute the most efficiently agents over the area to patrol in space and time, which constitutes a decision-making problem. A range of algorithms based on reactive, cognitive, reinforcement learning, centralised and decentralised strategies, amongst others, have been developed to make such a task ever more efficient. However, the existing patrolling-specific approaches based on supervised learning were still at preliminary stages, although a few works addressed this issue. Central to supervised learning, which is a set of methods and tools that allow inferring new knowledge, is the idea of learning a function mapping any input to an output from a sample of data composed of input-output pairs; learning, in this case, enables the system to generalise to new data never observed before. Until now, the best online MAP strategy, namely without precalculation, has turned out to be a centralised strategy with a coordinator. However, as for any centralised decision process in general, such a strategy is hardly scalable. The purpose of this work is then to develop and implement a new methodology aiming at turning any high-performance centralised strategy into a distributed strategy. Indeed, distributed strategies are by design resilient, more adaptive to changes in the environment, and scalable. In doing so, the centralised decision process, generally represented in MAP by a coordinator, is distributed into patrolling agents by means of supervised learning methods, so that each agent of the resultant distributed strategy tends to capture a part of the algorithm executed by the centralised decision process. The outcome is a new distributed decision-making algorithm based on machine learning. In this dissertation therefore, such a procedure of distribution of centralised strategy is established, then concretely implemented using some artificial neural networks architectures. By doing so, after having exposed the context and motivations of this work, we pose the problematic that led our study. The main multiagent strategies devised until now as part of MAP are then described, particularly a high-performance coordinated strategy, which is the centralised strategy studied in this work, as well as a simple decentralised strategy used as reference for decentralised strategies. Among others, some existing strategies based on supervised learning are also described. Thereafter, the model as well as certain of key concepts of MAP are defined. We also define the methodology laid down to address and study this problematic. This methodology comes in the form of a procedure that allows decentralising any centralised strategy by means of supervised learning. Then, the software ecosystem we developed for the needs of this work is also described, particularly PyTrol a discrete-time simulator dedicated to MAP developed with the aim of performing MAP simulation, to assess strategies and generate data, and MAPTrainer, a framework hinging on the PyTorch machine learning library, dedicated to research in machine learning in the context of MAP
Chandra, Siddhartha. „Apprentissage Profond pour des Prédictions Structurées Efficaces appliqué à la Classification Dense en Vision par Ordinateur“. Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC033/document.
Der volle Inhalt der QuelleIn this thesis we propose a structured prediction technique that combines the virtues of Gaussian Conditional Random Fields (G-CRFs) with Convolutional Neural Networks (CNNs). The starting point of this thesis is the observation that while being of a limited form GCRFs allow us to perform exact Maximum-APosteriori (MAP) inference efficiently. We prefer exactness and simplicity over generality and advocate G-CRF based structured prediction in deep learning pipelines. Our proposed structured prediction methods accomodate (i) exact inference, (ii) both shortand long- term pairwise interactions, (iii) rich CNN-based expressions for the pairwise terms, and (iv) end-to-end training alongside CNNs. We devise novel implementation strategies which allow us to overcome memory and computational challenges
Chen, Mickaël. „Learning with weak supervision using deep generative networks“. Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS024.
Der volle Inhalt der QuelleMany successes of deep learning rely on the availability of massive annotated datasets that can be exploited by supervised algorithms. Obtaining those labels at a large scale, however, can be difficult, or even impossible in many situations. Designing methods that are less dependent on annotations is therefore a major research topic, and many semi-supervised and weakly supervised methods have been proposed. Meanwhile, the recent introduction of deep generative networks provided deep learning methods with the ability to manipulate complex distributions, allowing for breakthroughs in tasks such as image edition and domain adaptation. In this thesis, we explore how these new tools can be useful to further alleviate the need for annotations. Firstly, we tackle the task of performing stochastic predictions. It consists in designing systems for structured prediction that take into account the variability in possible outputs. We propose, in this context, two models. The first one performs predictions on multi-view data with missing views, and the second one predicts possible futures of a video sequence. Then, we study adversarial methods to learn a factorized latent space, in a setting with two explanatory factors but only one of them is annotated. We propose models that aim to uncover semantically consistent latent representations for those factors. One model is applied to the conditional generation of motion capture data, and another one to multi-view data. Finally, we focus on the task of image segmentation, which is of crucial importance in computer vision. Building on previously explored ideas, we propose a model for object segmentation that is entirely unsupervised
Duran, Audrey. „Intelligence artificielle pour la caractérisation du cancer de la prostate par agressivité en IRM multiparamétrique“. Thesis, Lyon, 2022. http://theses.insa-lyon.fr/publication/2022LYSEI008/these.pdf.
Der volle Inhalt der QuelleProstate cancer (PCa) is the most frequently diagnosed cancer in men in more than half the countries in the world and the fifth leading cause of cancer death among men in 2020. Diagnosis of PCa includes multiparametric magnetic resonance imaging acquisition (mp-MRI) - which combines T2 weighted (T2-w), diffusion weighted imaging (DWI) and dynamic contrast enhanced (DCE) sequences - prior to any biopsy. The joint analysis of these multimodal images is time demanding and challenging, especially when individual MR sequences yield conflicting findings. In addition, the sensitivity of MRI is low for less aggressive cancers and inter-reader reproducibility remains moderate at best. Moreover, visual analysis does not currently allow to determine the cancer aggressiveness, characterized by the Gleason score (GS). This is why computer-aided diagnosis (CAD) systems based on statistical learning models have been proposed in recent years, to assist radiologists in their diagnostic task, but the vast majority of these models focus on the binary detection of clinically significant (CS) lesions. The objective of this thesis is to develop a CAD system to detect and segment PCa on mp-MRI images but also to characterize their aggressiveness, by predicting the associated GS. In a first part, we present a supervised CAD system to segment PCa by aggressiveness from T2-w and ADC maps. This end-to-end multi-class neural network jointly segments the prostate gland and cancer lesions with GS group grading. The model was trained and validated with a 5-fold cross-validation on a heterogeneous series of 219 MRI exams acquired on three different scanners prior prostatectomy. Regarding the automatic GS group grading, Cohen’s quadratic weighted kappa coefficient (κ) is 0.418 ± 0.138, which is the best reported lesion-wise kappa for GS segmentation to our knowledge. The model has also encouraging generalization capacities on the PROSTATEx-2 public dataset. In a second part, we focus on a weakly supervised model that allows the inclusion of partly annotated data, where the lesions are identified by points only, for a consequent saving of time and the inclusion of biopsy-based databases. Regarding the automatic GS group grading on our private dataset, we show that we can approach performance achieved with the baseline fully supervised model while considering 6% of annotated voxels only for training. In the last part, we study the contribution of DCE MRI, a sequence often omitted as input to deep models, for the detection and characterization of PCa. We evaluate several ways to encode the perfusion from the DCE MRI information in a U-Net like architecture. Parametric maps derived from DCE MR exams are shown to positively impact segmentation and grading performance of PCa lesions
Gal, Viviane. „Vers une nouvelle Interaction Homme Environnement dans les jeux vidéo et pervasifs : rétroaction biologique et états émotionnels : apprentissage profond non supervisé au service de l'affectique“. Electronic Thesis or Diss., Paris, CNAM, 2019. http://www.theses.fr/2019CNAM1269.
Der volle Inhalt der QuelleLiving exceptional moments, experiencing thrills, well-being, blooming, are often part of our dreams or aspirations. We choose various ways to get there like games. Whether the player is looking for originality, challenges, discovery, a story, or other goals, emotional states are the purpose of his quest. He remains until the game gives him pleasure, sensations. How bring them there? We are developing a new human environment interaction that takes into account and adapts to emotions. We address video or pervasive games or other applications. Through this goal, players should not be bothered by interfaces, or biosensors invasivness. This work raises two questions:- Can we discover emotional states based on physiological measurements from contact biosensors?- If so, can these sensors be replaced by remote, non-invasive devices and produce the same results?The models we have developed propose solutions based on unsupervised machine learning methods. We also present remote measurements technics and explain our future works in a new field we call affectics
Aversano, Gianmarco. „Development of physics-based reduced-order models for reacting flow applications“. Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLC095/document.
Der volle Inhalt der QuelleWith the final objective being to developreduced-order models for combustion applications,unsupervised and supervised machine learningtechniques were tested and combined in the workof the present Thesis for feature extraction and theconstruction of reduced-order models. Thus, the applicationof data-driven techniques for the detection offeatures from turbulent combustion data sets (directnumerical simulation) was investigated on two H2/COflames: a spatially-evolving (DNS1) and a temporallyevolvingjet (DNS2). Methods such as Principal ComponentAnalysis (PCA), Local Principal ComponentAnalysis (LPCA), Non-negative Matrix Factorization(NMF) and Autoencoders were explored for this purpose.It was shown that various factors could affectthe performance of these methods, such as the criteriaemployed for the centering and the scaling of theoriginal data or the choice of the number of dimensionsin the low-rank approximations. A set of guidelineswas presented that can aid the process ofidentifying meaningful physical features from turbulentreactive flows data. Data compression methods suchas Principal Component Analysis (PCA) and variationswere combined with interpolation methods suchas Kriging, for the construction of computationally affordablereduced-order models for the prediction ofthe state of a combustion system for unseen operatingconditions or combinations of model input parametervalues. The methodology was first tested forthe prediction of 1D flames with an increasing numberof input parameters (equivalence ratio, fuel compositionand inlet temperature), with variations of the classicPCA approach, namely constrained PCA and localPCA, being applied to combustion cases for the firsttime in combination with an interpolation technique.The positive outcome of the study led to the applicationof the proposed methodology to 2D flames withtwo input parameters, namely fuel composition andinlet velocity, which produced satisfactory results. Alternativesto the chosen unsupervised and supervisedmethods were also tested on the same 2D data.The use of non-negative matrix factorization (NMF) forlow-rank approximation was investigated because ofthe ability of the method to represent positive-valueddata, which helps the non-violation of important physicallaws such as positivity of chemical species massfractions, and compared to PCA. As alternative supervisedmethods, the combination of polynomial chaosexpansion (PCE) and Kriging and the use of artificialneural networks (ANNs) were tested. Results from thementioned work paved the way for the developmentof a digital twin of a combustion furnace from a setof 3D simulations. The combination of PCA and Krigingwas also employed in the context of uncertaintyquantification (UQ), specifically in the bound-to-bounddata collaboration framework (B2B-DC), which led tothe introduction of the reduced-order B2B-DC procedureas for the first time the B2B-DC was developedin terms of latent variables and not in terms of originalphysical variables
Oquab, Maxime. „Convolutional neural networks : towards less supervision for visual recognition“. Thesis, Paris Sciences et Lettres (ComUE), 2018. http://www.theses.fr/2018PSLEE061.
Der volle Inhalt der QuelleConvolutional Neural Networks are flexible learning algorithms for computer vision that scale particularly well with the amount of data that is provided for training them. Although these methods had successful applications already in the ’90s, they were not used in visual recognition pipelines because of their lesser performance on realistic natural images. It is only after the amount of data and the computational power both reached a critical point that these algorithms revealed their potential during the ImageNet challenge of 2012, leading to a paradigm shift in visual recogntion. The first contribution of this thesis is a transfer learning setup with a Convolutional Neural Network for image classification. Using a pre-training procedure, we show that image representations learned in a network generalize to other recognition tasks, and their performance scales up with the amount of data used in pre-training. The second contribution of this thesis is a weakly supervised setup for image classification that can predict the location of objects in complex cluttered scenes, based on a dataset indicating only with the presence or absence of objects in training images. The third contribution of this thesis aims at finding possible paths for progress in unsupervised learning with neural networks. We study the recent trend of Generative Adversarial Networks and propose two-sample tests for evaluating models. We investigate possible links with concepts related to causality, and propose a two-sample test method for the task of causal discovery. Finally, building on a recent connection with optimal transport, we investigate what these generative algorithms are learning from unlabeled data
De, La Bourdonnaye François. „Learning sensori-motor mappings using little knowledge : application to manipulation robotics“. Thesis, Université Clermont Auvergne (2017-2020), 2018. http://www.theses.fr/2018CLFAC037/document.
Der volle Inhalt der QuelleThe thesis is focused on learning a complex manipulation robotics task using little knowledge. More precisely, the concerned task consists in reaching an object with a serial arm and the objective is to learn it without camera calibration parameters, forward kinematics, handcrafted features, or expert demonstrations. Deep reinforcement learning algorithms suit well to this objective. Indeed, reinforcement learning allows to learn sensori-motor mappings while dispensing with dynamics. Besides, deep learning allows to dispense with handcrafted features for the state spacerepresentation. However, it is difficult to specify the objectives of the learned task without requiring human supervision. Some solutions imply expert demonstrations or shaping rewards to guiderobots towards its objective. The latter is generally computed using forward kinematics and handcrafted visual modules. Another class of solutions consists in decomposing the complex task. Learning from easy missions can be used, but this requires the knowledge of a goal state. Decomposing the whole complex into simpler sub tasks can also be utilized (hierarchical learning) but does notnecessarily imply a lack of human supervision. Alternate approaches which use several agents in parallel to increase the probability of success can be used but are costly. In our approach,we decompose the whole reaching task into three simpler sub tasks while taking inspiration from the human behavior. Indeed, humans first look at an object before reaching it. The first learned task is an object fixation task which is aimed at localizing the object in the 3D space. This is learned using deep reinforcement learning and a weakly supervised reward function. The second task consists in learning jointly end-effector binocular fixations and a hand-eye coordination function. This is also learned using a similar set-up and is aimed at localizing the end-effector in the 3D space. The third task uses the two prior learned skills to learn to reach an object and uses the same requirements as the two prior tasks: it hardly requires supervision. In addition, without using additional priors, an object reachability predictor is learned in parallel. The main contribution of this thesis is the learning of a complex robotic task with weak supervision
Aklil, Nassim. „Apprentissage actif sous contrainte de budget en robotique et en neurosciences computationnelles. Localisation robotique et modélisation comportementale en environnement non stationnaire“. Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066225/document.
Der volle Inhalt der QuelleDecision-making is a highly researched field in science, be it in neuroscience to understand the processes underlying animal decision-making, or in robotics to model efficient and rapid decision-making processes in real environments. In neuroscience, this problem is resolved online with sequential decision-making models based on reinforcement learning. In robotics, the primary objective is efficiency, in order to be deployed in real environments. However, in robotics what can be called the budget and which concerns the limitations inherent to the hardware, such as computation times, limited actions available to the robot or the lifetime of the robot battery, are often not taken into account at the present time. We propose in this thesis to introduce the notion of budget as an explicit constraint in the robotic learning processes applied to a localization task by implementing a model based on work developed in statistical learning that processes data under explicit constraints, limiting the input of data or imposing a more explicit time constraint. In order to discuss an online functioning of this type of budgeted learning algorithms, we also discuss some possible inspirations that could be taken on the side of computational neuroscience. In this context, the alternation between information retrieval for location and the decision to move for a robot may be indirectly linked to the notion of exploration-exploitation compromise. We present our contribution to the modeling of this compromise in animals in a non-stationary task involving different levels of uncertainty, and we make the link with the methods of multi-armed bandits
Jezequel, Loïc. „Vers une détection d'anomalie unifiée avec une application à la détection de fraude“. Electronic Thesis or Diss., CY Cergy Paris Université, 2023. http://www.theses.fr/2023CYUN1190.
Der volle Inhalt der QuelleDetecting observations straying apart from a baseline case is becoming increasingly critical in many applications. It is found in fraud detection, medical imaging, video surveillance or even in manufacturing defect detection with data ranging from images to sound. Deep anomaly detection was introduced to tackle this challenge by properly modeling the normal class, and considering anything significantly different as anomalous. Given the anomalous class is not well-defined, classical binary classification will not be suitable and lack robustness and reliability outside its training domain. Nevertheless, the best-performing anomaly detection approaches still lack generalization to different types of anomalies. Indeed, each method is either specialized on high-scale object anomalies or low-scale local anomalies.In this context, we first introduce a more generic one-class pretext-task anomaly detector. The model, named OC-MQ, computes an anomaly score by learning to solve a complex pretext task on the normal class. The pretext task is composed of several sub-tasks allowing it to capture a wide variety of visual cues. More specifically, our model is made of two branches each representing discriminative and generative tasks.Nevertheless, an additional anomalous dataset is in reality often available in many applications and can provide harder edge-case anomalous examples. In this light, we explore two approaches for outlier-exposure. First, we generalize the concept of pretext task to outlier-exposure by dynamically learning the pretext task itself with normal and anomalous samples. We propose two the models SadTPS and SadRest that respectively learn a discriminative pretext task of thin plate transform recognition and generative task of image restoration. In addition, we present a new anomaly-distance model SadCLR, where the training of previously unreliable anomaly-distance models is stabilized by adding contrastive regularization on the representation direction. We further enrich existing anomalies by generating several types of pseudo-anomalies.Finally, we extend the two previous approaches to be usable in both one-class and outlier-exposure setting. Firstly, we introduce the AnoMem model which memorizes a set of multi-scale normal prototypes by using modern Hopfield layers. Anomaly distance estimators are then fitted on the deviations between the input and normal prototypes in a one-class or outlier-exposure manner. Secondly, we generalize learnable pretext tasks to be learned only using normal samples. Our proposed model HEAT adversarially learns the pretext task to be just challenging enough to keep good performance on normal samples, while failing on anomalies. Besides, we choose the recently proposed Busemann distance in the hyperbolic Poincaré ball model to compute the anomaly score.Extensive testing was conducted for each proposed method, varying from coarse and subtle style anomalies to a fraud detection dataset of face presentation attacks with local anomalies. These tests yielded state-of-the-art results, showing the significant success of our methods
Blot, Michaël. „Étude de l'apprentissage et de la généralisation des réseaux profonds en classification d'images“. Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS412.
Der volle Inhalt der QuelleArtificial intelligence is experiencing a resurgence in recent years. This is due to the growing ability to collect and store a considerable amount of digitized data. These huge databases allow machine learning algorithms to respond to certain tasks through supervised learning. Among the digitized data, images remain predominant in the modern environment. Huge datasets have been created. moreover, the image classification has allowed the development of previously neglected models, deep neural networks or deep learning. This family of algorithms demonstrates a great facility to learn perfectly datasets, even very large. Their ability to generalize remains largely misunderstood, but the networks of convolutions are today the undisputed state of the art. From a research and application point of view of deep learning, the demands will be more and more demanding, requiring to make an effort to bring the performances of the neuron networks to the maximum of their capacities. This is the purpose of our research, whose contributions are presented in this thesis. We first looked at the issue of training and considered accelerating it through distributed methods. We then studied the architectures in order to improve them without increasing their complexity. Finally, we particularly study the regularization of network training. We studied a regularization criterion based on information theory that we deployed in two different ways
Prost, Vincent. „Sparse unsupervised learning for metagenomic data“. Electronic Thesis or Diss., université Paris-Saclay, 2020. http://www.theses.fr/2020UPASL013.
Der volle Inhalt der QuelleThe development of massively parallel sequencing technologies enables to sequence DNA at high-throughput and low cost, fueling the rise of metagenomics which is the study of complex microbial communities sequenced in their natural environment.Metagenomic problems are usually computationally difficult and are further complicated by the massive amount of data involved.In this thesis we consider two different metagenomics problems: 1. raw reads binning and 2. microbial network inference from taxonomic abundance profiles. We address them using unsupervised machine learning methods leveraging the parsimony principle, typically involving l1 penalized log-likelihood maximization.The assembly of genomes from raw metagenomic datasets is a challenging task akin to assembling a mixture of large puzzles composed of billions or trillions of pieces (DNA sequences). In the first part of this thesis, we consider the related task of clustering sequences into biologically meaningful partitions (binning). Most of the existing computational tools perform binning after read assembly as a pre-processing, which is error-prone (yielding artifacts like chimeric contigs) and discards vast amounts of information in the form of unassembled reads (up to 50% for highly diverse metagenomes). This motivated us to try to address the raw read binning (without prior assembly) problem. We exploit the co-abundance of species across samples as discriminative signal. Abundance is usually measured via the number of occurrences of long k-mers (subsequences of size k). The use of Local Sensitive Hashing (LSH) allows us to contain, at the cost of some approximation, the combinatorial explosion of long k-mers indexing. The first contribution of this thesis is to propose a sparse Non-Negative Matrix factorization (NMF) of the samples x k-mers count matrix in order to extract abundance variation signals. We first show that using sparse NMF is well-grounded since data is a sparse linear mixture of non-negative components. Sparse NMF exploiting online dictionary learning algorithms retained our attention, including its decent behavior on largely asymmetric data matrices. The validation of metagenomic binning being difficult on real datasets, because of the absence of ground truth, we created and used several benchmarks for the different methods evaluated on. We illustrated that sparse NMF improves state of the art binning methods on those datasets. Experiments conducted on a real metagenomic cohort of 1135 human gut microbiota showed the relevance of the approach.In the second part of the thesis, we consider metagenomic data after taxonomic profiling: multivariate data representing abundances of taxa across samples. It is known that microbes live in communities structured by ecological interaction between the members of the community. We focus on the problem of the inference of microbial interaction networks from taxonomic profiles. This problem is frequently cast into the paradigm of Gaussian graphical models (GGMs) for which efficient structure inference algorithms are available, like the graphical lasso. Unfortunately, GGMs or variants thereof can not properly account for the extremely sparse patterns occurring in real-world metagenomic taxonomic profiles. In particular, structural zeros corresponding to true absences of biological signals fail to be properly handled by most statistical methods. We present in this part a zero-inflated log-normal graphical model specifically aimed at handling such "biological" zeros, and demonstrate significant performance gains over state-of-the-art statistical methods for the inference of microbial association networks, with most notable gains obtained when analyzing taxonomic profiles displaying sparsity levels on par with real-world metagenomic datasets
Hocquet, Guillaume. „Class Incremental Continual Learning in Deep Neural Networks“. Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPAST070.
Der volle Inhalt der QuelleWe are interested in the problem of continual learning of artificial neural networks in the case where the data are available for only one class at a time. To address the problem of catastrophic forgetting that restrain the learning performances in these conditions, we propose an approach based on the representation of the data of a class by a normal distribution. The transformations associated with these representations are performed using invertible neural networks, which can be trained with the data of a single class. Each class is assigned a network that will model its features. In this setting, predicting the class of a sample corresponds to identifying the network that best fit the sample. The advantage of such an approach is that once a network is trained, it is no longer necessary to update it later, as each network is independent of the others. It is this particularly advantageous property that sets our method apart from previous work in this area. We support our demonstration with experiments performed on various datasets and show that our approach performs favorably compared to the state of the art. Subsequently, we propose to optimize our approach by reducing its impact on memory by factoring the network parameters. It is then possible to significantly reduce the storage cost of these networks with a limited performance loss. Finally, we also study strategies to produce efficient feature extractor models for continual learning and we show their relevance compared to the networks traditionally used for continual learning
Putina, Andrian. „Unsupervised anomaly detection : methods and applications“. Electronic Thesis or Diss., Institut polytechnique de Paris, 2022. http://www.theses.fr/2022IPPAT012.
Der volle Inhalt der QuelleAn anomaly (also known as outlier) is an instance that significantly deviates from the rest of the input data and being defined by Hawkins as 'an observation, which deviates so much from other observations as to arouse suspicions that it was generated by a different mechanism'. Anomaly detection (also known as outlier or novelty detection) is thus the machine learning and data mining field with the purpose of identifying those instances whose features appear to be inconsistent with the remainder of the dataset. In many applications, correctly distinguishing the set of anomalous data points (outliers) from the set of normal ones (inliers) proves to be very important. A first application is data cleaning, i.e., identifying noisy and fallacious measurement in a dataset before further applying learning algorithms. However, with the explosive growth of data volume collectable from various sources, e.g., card transactions, internet connections, temperature measurements, etc. the use of anomaly detection becomes a crucial stand-alone task for continuous monitoring of the systems. In this context, anomaly detection can be used to detect ongoing intrusion attacks, faulty sensor networks or cancerous masses.The thesis proposes first a batch tree-based approach for unsupervised anomaly detection, called 'Random Histogram Forest (RHF)'. The algorithm solves the curse of dimensionality problem using the fourth central moment (aka kurtosis) in the model construction while boasting linear running time. A stream based anomaly detection engine, called 'ODS', that leverages DenStream, an unsupervised clustering technique is presented subsequently and finally Automated Anomaly Detection engine which alleviates the human effort required when dealing with several algorithm and hyper-parameters is presented as last contribution
Pascal, Barbara. „Estimation régularisée d'attributs fractals par minimisation convexe pour la segmentation de textures : formulations variationnelles conjointes, algorithmes proximaux rapides et sélection non supervisée des paramètres de régularisation; Applications à l'étude du frottement solide et de la microfluidique des écoulements multiphasiques“. Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEN042.
Der volle Inhalt der QuelleIn this doctoral thesis several scale-free texture segmentation procedures based on two fractal attributes, the Hölder exponent, measuring the local regularity of a texture, and local variance, are proposed.A piecewise homogeneous fractal texture model is built, along with a synthesis procedure, providing images composed of the aggregation of fractal texture patches with known attributes and segmentation. This synthesis procedure is used to evaluate the proposed methods performance.A first method, based on the Total Variation regularization of a noisy estimate of local regularity, is illustrated and refined thanks to a post-processing step consisting in an iterative thresholding and resulting in a segmentation.After evidencing the limitations of this first approach, deux segmentation methods, with either "free" or "co-located" contours, are built, taking in account jointly the local regularity and the local variance.These two procedures are formulated as convex nonsmooth functional minimization problems.We show that the two functionals, with "free" and "co-located" penalizations, are both strongly-convex. and compute their respective strong convexity moduli.Several minimization schemes are derived, and their convergence speed are compared.The segmentation performance of the different methods are evaluated over a large amount of synthetic data in configurations of increasing difficulty, as well as on real world images, and compared to state-of-the-art procedures, including convolutional neural networks.An application for the segmentation of multiphasic flow through a porous medium experiment images is presented.Finally, a strategy for automated selection of the hyperparameters of the "free" and "co-located" functionals is built, inspired from the SURE estimator of the quadratic risk
Tarbouriech, Jean. „Goal-oriented exploration for reinforcement learning“. Electronic Thesis or Diss., Université de Lille (2022-....), 2022. http://www.theses.fr/2022ULILB014.
Der volle Inhalt der QuelleLearning to reach goals is a competence of high practical relevance to acquire for intelligent agents. For instance, this encompasses many navigation tasks ("go to target X"), robotic manipulation ("attain position Y of the robotic arm"), or game-playing scenarios ("win the game by fulfilling objective Z"). As a living being interacting with the world, I am constantly driven by goals to reach, varying in scope and difficulty.Reinforcement Learning (RL) holds the promise to frame and learn goal-oriented behavior. Goals can be modeled as specific configurations of the environment that must be attained via sequential interaction and exploration of the unknown environment. Although various deep RL algorithms have been proposed for goal-oriented RL, existing methods often lack principled understanding, sample efficiency and general-purpose effectiveness. In fact, very limited theoretical analysis of goal-oriented RL was available, even in the basic scenario of finitely many states and actions.We first focus on a supervised scenario of goal-oriented RL, where a goal state to be reached in minimum total expected cost is provided as part of the problem definition. After formalizing the online learning problem in this setting often known as Stochastic Shortest Path (SSP), we introduce two no-regret algorithms (one is the first available in the literature, the other attains nearly optimal guarantees).Beyond training our RL agent to solve only one task, we then aspire that it learns to autonomously solve a wide variety of tasks, in the absence of any reward supervision. In this challenging unsupervised RL scenario, we advocate to "Set Your Own Goals" (SYOG), which suggests the agent to learn the ability to intrinsically select and reach its own goal states. We derive finite-time guarantees of this popular heuristic in various settings, each with its specific learning objective and technical challenges. As an illustration, we propose a rigorous analysis of the algorithmic principle of targeting "uncertain" goals which we also anchor in deep RL.The main focus and contribution of this thesis are to instigate a principled analysis of goal-oriented exploration in RL, both in the supervised and unsupervised scenarios. We hope that it helps suggest promising research directions to improve the interpretability and sample efficiency of goal-oriented RL algorithms in practical applications
Pusiol, Guido Thomas. „Découvertes d'activités humaines dans des videos“. Phd thesis, Université Nice Sophia Antipolis, 2012. http://tel.archives-ouvertes.fr/tel-00944617.
Der volle Inhalt der QuelleChahla, Charbel. „Non-linear feature extraction for object re-identification in cameras networks“. Thesis, Troyes, 2017. http://www.theses.fr/2017TROY0023.
Der volle Inhalt der QuelleReplicating the visual system that the brain uses to process the information is an area of substantial interest. This thesis is situated in the context of a fully automated system capable of analyzing facial features when the target is near the cameras, and tracking his identity when his facial features are no more traceable. The first part of this thesis is devoted to face pose estimation procedures to be used in face recognition scenarios. We proposed a new label-sensitive embedding based on a sparse representation called Sparse Label sensitive Locality Preserving Projections. In an uncontrolled environment observed by cameras from an unknown distance, person re-identification relying upon conventional biometrics such as face recognition is not feasible. Instead, visual features based on the appearance of people can be exploited more reliably. In this context, we propose a new embedding scheme for single-shot person re-identification under non overlapping target cameras. Each person is described as a vector of kernel similarities to a collection of prototype person images. The robustness of the algorithm is improved by proposing the Color Categorization procedure. In the last part of this thesis, we propose a Siamese architecture of two Convolutional Neural Networks (CNN), with each CNN reduced to only eleven layers. This architecture allows a machine to be fed directly with raw data and to automatically discover the representations needed for classification
Desir, Chesner. „Classification Automatique d'Images, Application à l'Imagerie du Poumon Profond“. Phd thesis, Université de Rouen, 2013. http://tel.archives-ouvertes.fr/tel-00879356.
Der volle Inhalt der QuelleDesir, Chesner. „Classification automatique d'images, application à l'imagerie du poumon profond“. Phd thesis, Rouen, 2013. http://www.theses.fr/2013ROUES053.
Der volle Inhalt der QuelleThis thesis deals with automated image classification, applied to images acquired with alveoscopy, a new imaging technique of the distal lung. The aim is to propose and develop a computer aided-diagnosis system, so as to help the clinician analyze these images never seen before. Our contributions lie in the development of effective, robust and generic methods to classify images of healthy and pathological patients. Our first classification system is based on a rich and local characterization of the images, an ensemble of random trees approach for classification and a rejection mechanism, providing the medical expert with tools to enhance the reliability of the system. Due to the complexity of alveoscopy images and to the lack of expertize on the pathological cases (unlike healthy cases), we adopt the one-class learning paradigm which allows to learn a classifier from healthy data only. We propose a one-class approach taking advantage of combining and randomization mechanisms of ensemble methods to respond to common issues such as the curse of dimensionality. Our method is shown to be effective, robust to the dimension, competitive and even better than state-of-the-art methods on various public datasets. It has proved to be particularly relevant to our medical problem
Gonthier, Nicolas. „Transfer learning of convolutional neural networks for texture synthesis and visual recognition in artistic images“. Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG024.
Der volle Inhalt der QuelleIn this thesis, we study the transfer of Convolutional Neural Networks (CNN) trained on natural images to related tasks. We follow two axes: texture synthesis and visual recognition in artworks. The first one consists in synthesizing a new image given a reference sample. Most methods are based on enforcing the Gram matrices of ImageNet-trained CNN features. We develop a multi-resolution strategy to take into account large scale structures. This strategy can be coupled with long-range constraints either through a Fourier frequency constraint, or the use of feature maps autocorrelation. This scheme allows excellent high-resolution synthesis especially for regular textures. We compare our methods to alternatives ones with quantitative and perceptual evaluations. In a second axis, we focus on transfer learning of CNN for artistic image classification. CNNs can be used as off-the-shelf feature extractors or fine-tuned. We illustrate the advantage of the last solution. Second, we use feature visualization techniques, CNNs similarity indexes and quantitative metrics to highlight some characteristics of the fine-tuning process. Another possibility is to transfer a CNN trained for object detection. We propose a simple multiple instance method using off-the-shelf deep features and box proposals, for weakly supervised object detection. At training time, only image-level annotations are needed. We experimentally show the interest of our models on six non-photorealistic
Grelier, Erwan. „Learning with tree-based tensor formats : Application to uncertainty quantification in vibroacoustics“. Thesis, Ecole centrale de Nantes, 2019. http://www.theses.fr/2019ECDN0070.
Der volle Inhalt der QuelleMany problems require the evaluation of complex parametrized models for many instances of the parameters, particularly for uncertainty quantification. When the model is costly to evaluate, it is usually approximated by another model cheaper to evaluate. The aim of this thesis is to develop statistical learning methods using model classes of functions in treebased tensor formats for the approximation of highdimensional functions, both for supervised and unsupervised learning tasks. These model classes, which are rank-structured functions parametrized by a tree-structured network of low-order tensors, can be interpreted as deep neural networks with particular architecture and activation functions. The approximation is obtained by empirical risk minimization over the set of functions in tree-based tensor format. For a high-dimensional function, or when little information on the function is available, the model class has to be carefully selected. We propose stable learning algorithms that adapt the tree and ranks and select the model based on crossvalidation estimates. Furthermore, some functions might only exhibit a low-rank structure after a suitable change of variables. For such cases, we propose adaptive learning algorithms with model classes combining tree-based tensor formats and changes of variables. The proposed algorithms are applied to uncertainty quantification in vibroacoustics. This thesis is included in the Joint Laboratory of Marine Technology between Naval Group, Centrale Nantes and Université de Nantes, and in the Eval-PI project
Bovée, Samuel. „Le regard dans les interactions lors d’entretiens en face à face et son analyse parmi les signaux sociaux“. Caen, 2016. http://www.theses.fr/2016CAEN2047.
Der volle Inhalt der QuelleOral communication plays a key role in social and professional relations. Face-to-face interview, appreciated in managerial and commercial areas, remains the richest human interpersonal interaction thanks to innate and joint use of verbal and non-verbal social cues. That is the reason why at Zero to One Technology, we develop a diagnostic and pedagogical tool : the Comscope. With simulated and recorded interview practicing, then by extracting and analyzing automatically social cues, it provides measurement of the quality of the interaction in order to improve it. The research for this thesis is principally directed towards the analysis of gaze signal. In order to do so, we created new estimators for head-pose, gaze direction and time of focus of attention on the interlocutor. All the estimators are based on facial landmarks detection and iris location extraction. By use of low-resolution video recording devices in visible light, they must work together in real time and in uncontrolled environment. We also created away of assessing automatically the technical quality of an interview by classification. We used the features extracted from gaze (eye movements and fixations, time of attention), speech (speaking time estimation and transcript of exchange : lexicology analysis, interview labelling), and their multimodal and crossed analysis
Rastin, Parisa. „Automatic and Adaptive Learning for Relational Data Stream Clustering“. Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD052.
Der volle Inhalt der QuelleThe research work presented in this thesis concerns the development of unsupervised learning approaches adapted to large relational and dynamic data-sets. The combination of these three characteristics (size, complexity and evolution) is a major challenge in the field of data mining and few satisfactory solutions exist at the moment, despite the obvious needs of companies. This is a real challenge, because the approaches adapted to relational data have a quadratic complexity, unsuited to the analysis of dynamic data. We propose here two complementary approaches for the analysis of this type of data. The first approach is able to detect well-separated clusters from a signal created during an incremental reordering of the dissimilarity matrix, with no parameter to choose (e.g., the number of clusters). The second proposes to use support points among the objects in order to build a representation space to define representative prototypes of the clusters. Finally, we apply the proposed approaches to real-time profiling of connected users. Profiling tasks are designed to recognize the "state of mind" of users through their navigations on different web-sites