Добірка наукової літератури з теми "Espace de représentation / Espace latent"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Espace de représentation / Espace latent".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Espace de représentation / Espace latent":
Mésini, Béatrice. "Les Sans dans les forums sociaux. Luttes aux confins et lignes de confront." Note de recherche 28, no. 1 (May 21, 2009): 193–228. http://dx.doi.org/10.7202/001730ar.
Sène, Abdourahmane Mbade. "Conflit Autour d’Un Espace Protégé : Cas du Parc National de Basse Casamance." European Scientific Journal, ESJ 19, no. 5 (February 28, 2023): 36. http://dx.doi.org/10.19044/esj.2023.v19n5p36.
Kwaterko, Józef. "Espace urbain, espace mnémonique." Études littéraires 23, no. 3 (April 12, 2005): 57–68. http://dx.doi.org/10.7202/500944ar.
Champagneetj, P., and P. Pagès. "Environnement, espace public et représentation." Espaces et sociétés 77, no. 3 (1994): 45. http://dx.doi.org/10.3917/esp.1994.77.0045.
Guay, Hervé. "Sade et Espace Libre." Dossier — Sade au théâtre : la scène et l’obscène, no. 41 (May 7, 2010): 103–18. http://dx.doi.org/10.7202/041673ar.
Masson, Michèle. "Espace vécu, représentation graphique et milieu culturel." Géographes associés 13, no. 1 (1993): 23–44. http://dx.doi.org/10.3406/geoas.1993.1851.
Guinebault-Szlamowicz, Chantal. "Fondements de la scénographie moderne : étymologie, histoire et esthétique." Figures de l'Art. Revue d'études esthétiques 18, no. 1 (2010): 23–36. http://dx.doi.org/10.3406/fdart.2010.887.
Fauteux, Martial. "Représentation de la ville." Cahiers de géographie du Québec 21, no. 52 (April 12, 2005): 83–103. http://dx.doi.org/10.7202/021354ar.
Biarez, Sylvie. "Sphère locale et espace public." Lien social et Politiques, no. 39 (October 2, 2002): 127–38. http://dx.doi.org/10.7202/005059ar.
Kopytina, Anastasiia, and Anastasiia Moskalenko. "REPRÉSENTATION VERBALE DE LA CATEGORIE DE L'ESPACE EN FRANÇAIS ET ITALIEN." Grail of Science, no. 36 (February 24, 2024): 297–300. http://dx.doi.org/10.36074/grail-of-science.16.02.2024.049.
Дисертації з теми "Espace de représentation / Espace latent":
Jouffroy, Emma. "Développement de modèles non supervisés pour l'obtention de représentations latentes interprétables d'images." Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0050.
The Laser Megajoule (LMJ) is a large research device that simulates pressure and temperature conditions similar to those found in stars. During experiments, diagnostics are guided into an experimental chamber for precise positioning. To minimize the risks associated with human error in such an experimental context, the automation of an anti-collision system is envisaged. This involves the design of machine learning tools offering reliable decision levels based on the interpretation of images from cameras positioned in the chamber. Our research focuses on probabilistic generative neural methods, in particular variational auto-encoders (VAEs). The choice of this class of models is linked to the fact that it potentially enables access to a latent space directly linked to the properties of the objects making up the observed scene. The major challenge is to study the design of deep network models that effectively enable access to such a fully informative and interpretable representation, with a view to system reliability. The probabilistic formalism intrinsic to VAE allows us, if we can trace back to such a representation, to access an analysis of the uncertainties of the encoded information
Prang, Mathieu. "Representation learning for symbolic music." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS489.
A key part in the recent success of deep language processing models lies in the ability to learn efficient word embeddings. These methods provide structured spaces of reduced dimensionality with interesting metric relationship properties. These, in turn, can be used as efficient input representations for handling more complex tasks. In this thesis, we focus on the task of learning embedding spaces for polyphonic music in the symbolic domain. To do so, we explore two different approaches.We introduce an embedding model based on a convolutional network with a novel type of self-modulated hierarchical attention, which is computed at each layer to obtain a hierarchical vision of musical information.Then, we propose another system based on VAEs, a type of auto-encoder that constrains the data distribution of the latent space to be close to a prior distribution. As polyphonic music information is very complex, the design of input representation is a crucial process. Hence, we introduce a novel representation of symbolic music data, which transforms a polyphonic score into a continuous signal.Finally, we show the potential of the resulting embedding spaces through the development of several creative applications used to enhance musical knowledge and expression, through tasks such as melodies modification or composer identification
Elguendouze, Sofiane. "Explainable Artificial Intelligence approaches for Image Captioning." Electronic Thesis or Diss., Orléans, 2024. http://www.theses.fr/2024ORLE1003.
The rapid advancement of image captioning models, driven by the integration of deep learning techniques that combine image and text modalities, has resulted in increasingly complex systems. However, these models often operate as black boxes, lacking the ability to provide transparent explanations for their decisions. This thesis addresses the explainability of image captioning systems based on Encoder-Attention-Decoder architectures, through four aspects. First, it explores the concept of the latent space, marking a departure from traditional approaches relying on the original representation space. Second, it introduces the notion of decisiveness, leading to the formulation of a new definition for the concept of component influence/decisiveness in the context of explainable image captioning, as well as a perturbation-based approach to capturing decisiveness. The third aspect aims to elucidate the factors influencing explanation quality, in particular the scope of explanation methods. Accordingly, latent-based variants of well-established explanation methods such as LRP and LIME have been developed, along with the introduction of a latent-centered evaluation approach called Latent Ablation. The fourth aspect of this work involves investigating what we call saliency and the representation of certain visual concepts, such as object quantity, at different levels of the captioning architecture
Morchid, Mohamed. "Représentations robustes de documents bruités dans des espaces homogènes." Thesis, Avignon, 2014. http://www.theses.fr/2014AVIG0202/document.
In the Information Retrieval field, documents are usually considered as a "bagof-words". This model does not take into account the temporal structure of thedocument and is sensitive to noises which can alter its lexical form. These noisescan be produced by different sources : uncontrolled form of documents in microbloggingplatforms, automatic transcription of speech documents which are errorprone,lexical and grammatical variabilities in Web forums. . . The work presented inthis thesis addresses issues related to document representations from noisy sources.The thesis consists of three parts in which different representations of content areavailable. The first one compares a classical representation based on a term-frequencyrepresentation to a higher level representation based on a topic space. The abstractionof the document content allows us to limit the alteration of the noisy document byrepresenting its content with a set of high-level features. Our experiments confirm thatmapping a noisy document into a topic space allows us to improve the results obtainedduring different information retrieval tasks compared to a classical approach based onterm frequency. The major problem with such a high-level representation is that it isbased on a space theme whose parameters are chosen empirically.The second part presents a novel representation based on multiple topic spaces thatallow us to solve three main problems : the closeness of the subjects discussed in thedocument, the tricky choice of the "right" values of the topic space parameters and therobustness of the topic-based representation. Based on the idea that a single representationof the contents cannot capture all the relevant information, we propose to increasethe number of views on a single document. This multiplication of views generates "artificial"observations that contain fragments of useful information. The first experimentvalidated the multi-view approach to represent noisy texts. However, it has the disadvantageof being very large and redundant and of containing additional variability associatedwith the diversity of views. In the second step, we propose a method based onfactor analysis to compact the different views and to obtain a new robust representationof low dimension which contains only the informative part of the document whilethe noisy variabilities are compensated. During a dialogue classification task, the compressionprocess confirmed that this compact representation allows us to improve therobustness of noisy document representation.Nonetheless, during the learning process of topic spaces, the document is consideredas a "bag-of-words" while many studies have showed that the word position in a7document is useful. A representation which takes into account the temporal structureof the document based on hyper-complex numbers is proposed in the third part. Thisrepresentation is based on the hyper-complex numbers of dimension four named quaternions.Our experiments on a classification task have showed the effectiveness of theproposed approach compared to a conventional "bag-of-words" representation
Fèvres, Jessica. "Infographie, images de synthèse et patrimoine monumental : espace de représentation, espace de médiation." Phd thesis, Université Michel de Montaigne - Bordeaux III, 2012. http://tel.archives-ouvertes.fr/tel-00751452.
Bideran, Jessica de. "Infographie, images de synthèse et patrimoine monumental : espace de représentation, espace de médiation." Thesis, Bordeaux 3, 2012. http://www.theses.fr/2012BOR30025/document.
This thesis raises the issue of the use of infographic techniques and synthetic imagery to represent vestiges of the past, in particular archaeological and architectural heritage. Our approach is multidisciplinary. Since infographic systems belong to the category of media-related and cultural inventions that have come into existence since World War II, our study aims to be comprehensive, drawing on Art History, Archaeology, Information and Communications Technology. Our intention is to look beyond the purely technical dimension and to analyse these systems as cultural spaces of representation, within the scientific community (“specialists”) and for the general public (“neophytes”). Representation of built heritage using infographic tools has of course not sprung up spontaneously overnight, whether in the public sphere or in the more restricted sphere of the research community. Although this phenomenon is of course closely correlated with the development of the IT sector, it would be simplistic to regard it only as a consequence of this technological revolution. Indeed, changes in the media and scientific fields have gone hand in hand. The conservation of historic monuments and archaeological sites, their listing as being of public interest and management for exhibition purposes, consequently gives rise to debate and controversy in both the scientific-research and institutional spheres. More generally, these matters raise the issue of “heritage”, as much for ideological as for historical reasons. The purpose, then, of this study is to identify the social and cultural factors that have led to the emergence and development of these practices, which involve a combination of graphics, information technology and scientific research. Thus defined, the context invites us to analyse the ways in which these tools have been used and appropriated by different players in the heritage industry. Finally, we need to consider the material aspect of these images and highlight the areas of mediation which these systems create. In conclusion, it would seem that these new modes of representation exemplify a hybridisation of communication practises and codes of meaning resulting from the mixing of “scientific” and “popular” culture
Channarond, Antoine. "Recherche de structure dans un graphe aléatoire : modèles à espace latent." Thesis, Paris 11, 2013. http://www.theses.fr/2013PA112338/document.
.This thesis addresses the clustering of the nodes of a graph, in the framework of randommodels with latent variables. To each node i is allocated an unobserved (latent) variable Zi and the probability of nodes i and j being connected depends conditionally on Zi and Zj . Unlike Erdos-Renyi's model, connections are not independent identically distributed; the latent variables rule the connection distribution of the nodes. These models are thus heterogeneous and their structure is fully described by the latent variables and their distribution. Hence we aim at infering them from the graph, which the only observed data.In both original works of this thesis, we propose consistent inference methods with a computational cost no more than linear with respect to the number of nodes or edges, so that large graphs can be processed in a reasonable time. They both are based on a study of the distribution of the degrees, which are normalized in a convenient way for the model.The first work deals with the Stochastic Blockmodel. We show the consistency of an unsupervised classiffcation algorithm using concentration inequalities. We deduce from it a parametric estimation method, a model selection method for the number of latent classes, and a clustering test (testing whether there is one cluster or more), which are all proved to be consistent. In the second work, the latent variables are positions in the ℝd space, having a density f. The connection probability depends on the distance between the node positions. The clusters are defined as connected components of some level set of f. The goal is to estimate the number of such clusters from the observed graph only. We estimate the density at the latent positions of the nodes with their degree, which allows to establish a link between clusters and connected components of some subgraphs of the observed graph, obtained by removing low degree nodes. In particular, we thus derive an estimator of the cluster number and we also show the consistency in some sense
Georgel, Christophe. "Architecture, espace et représentation en Lorraine à la Renaissance (1500-1550)." Université Marc Bloch (Strasbourg) (1971-2008), 2004. http://www.theses.fr/2004STR20021.
At the dawning of the Renaissance the stylistic renewel of the structure and symbolic functionality of the architectural space in Lorraine is analysed in three geographical styles interdependent historically : 1) the production of the ruling-class under the Dukes René II and Antoine situated around the ducal palace in Nancy. . . 2) the analysis of the "poetic threshold", of the draughtsmanship of the treaty, De Artificiali Perspectiva (Toul, 1505) by Jean Pèlerin. . . 3) from the introduction of the orders of the church of Blénod-lès-Toul. .
Garidi, Tarik. "Sur la théorie des champs dans l'espace-temps de de Sitter." Paris 7, 2003. http://www.theses.fr/2003PA077049.
Meliani, Abdelhai. "Etude macro économétrique de l'économie marocaine : représentation espace - état et contrôle optimal." Toulouse 1, 1990. http://www.theses.fr/1990TOU10012.
This study is aimed to propose an analytical framework for evaluating economic policies in morocco. It is the first attempt to our knowledge for applying optimal control methods in the Moroccan case. A macroeconometric model with 24 equations is built and estimated by two-stage least squares. Its short and long run properties are analysed by compunting multipliers and elasticities. It is then simulated. Its resolution is done by using space state representation and Kalman filter process. The practicability of these techniques is illustrated for the Moroccan case and sheds light on the conduct of macroeconomic policies. Various simulations show that the monetary policy plays a more efficient role in monitoring the real economy than the fiscal one. Results prove that the joint use of optimal control and kalman filter theories can be an invaluable assistance for the macroeconomic planning of Morocco
Книги з теми "Espace de représentation / Espace latent":
Marcos, Susana. Entre espace public et espace privé: Les élites en représentation. Perpignan]: Presses universitaires de Perpignan, 2018.
Augusta-Boularot, Sandrine, and Emmanuelle Rosso. Signa et tituli: Monuments et espaces de représentation en Gaule méridionale sous le regard croisé de la sculpture et de l'épigraphie. Arles: Errance, 2015.
Marcos, Susana, ed. Entre espace public et espace privé : les élites en représentation. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38257.
Temps, espace & représentation: Séminaire a l'occasion du Xeme anniversaire de la Faculté des lettres et des sciences humaines de Sousse 1990-2000. Sousse: Université du centre, Faculté des lettres et des sciences humaines, 2000.
Частини книг з теми "Espace de représentation / Espace latent":
FARINELLI, Franco. "Cartographie et production spatiale de la société." In Politiques de la carte, 55–76. ISTE Group, 2022. http://dx.doi.org/10.51926/iste.9067.ch2.
"Remerciements." In Entre espace public et espace privé : les élites en représentation, 5. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38287.
"Index des noms de personnages, divinités et peuples." In Entre espace public et espace privé : les élites en représentation, 159–61. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38382.
Álvarez Melero, Anthony. "Entre espace privé et public." In Entre espace public et espace privé : les élites en représentation, 59–73. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38327.
"Index des noms de lieux." In Entre espace public et espace privé : les élites en représentation, 156–58. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38377.
Marcos, Susana. "Introduction." In Entre espace public et espace privé : les élites en représentation, 7–12. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38292.
"Abréviations des sources." In Entre espace public et espace privé : les élites en représentation, 147–50. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38367.
Guizani, Samir. "Les espaces d’hygiène et de confort en Tunisie à l’époque romaine : les latrines privées." In Entre espace public et espace privé : les élites en représentation, 87–111. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38347.
Bertrand, Audrey. "Scènes italiennes." In Entre espace public et espace privé : les élites en représentation, 13–24. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38302.
Denjean, Claude. "Contrepoint." In Entre espace public et espace privé : les élites en représentation, 113–28. Presses universitaires de Perpignan, 2018. http://dx.doi.org/10.4000/books.pupvd.38357.
Тези доповідей конференцій з теми "Espace de représentation / Espace latent":
Darrault-Harris, Ivan, and Sonia Grubits. "Le paysage dessiné : un espace de projection identitaire." In Paysages & valeurs : de la représentation à la simulation. Limoges: Université de Limoges, 2008. http://dx.doi.org/10.25965/as.3477.
Van de Vreken, Anne, and Stéphane Safin. "Influence du type de représentation visuelle sur l'évaluation de l'ambiance d'un espace architectural." In Conference Internationale Francophone sur I'Interaction Homme-Machine. New York, New York, USA: ACM Press, 2010. http://dx.doi.org/10.1145/1941007.1941015.
Marcheix, Daniel. "Pierre Bergounioux et le paysage corrézien." In Paysages & valeurs : de la représentation à la simulation. Limoges: Université de Limoges, 2008. http://dx.doi.org/10.25965/as.3451.
García Fernández, Manuel Ángel. "Les représentations de l’eau dans les lais merveilleux bretons." In XXV Coloquio AFUE. Palabras e imaginarios del agua. Valencia: Universitat Politècnica València, 2016. http://dx.doi.org/10.4995/xxvcoloquioafue.2016.2978.
Petit, Stéphane. "L’étude des paysages alluviaux par les techniques de l’écologie du paysage." In Paysages & valeurs : de la représentation à la simulation. Limoges: Université de Limoges, 2008. http://dx.doi.org/10.25965/as.3416.
Griselin, Madeleine, Sébastien Nageleisen, and Serge Ormaux. "Entre le paysage-existence et le paysage-expérience, le paysage-itinérance." In Paysages & valeurs : de la représentation à la simulation. Limoges: Université de Limoges, 2008. http://dx.doi.org/10.25965/as.3441.