Descripteur
Termes IGN > mathématiques > statistique mathématique > analyse de données > classification > classification par réseau neuronal
classification par réseau neuronalVoir aussi |
Documents disponibles dans cette catégorie (563)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
Etendre la recherche sur niveau(x) vers le bas
Sparsity, redundancy and robustness in artificial neural networks for learning and memory / Philippe Tigréat (2017)
![]()
Titre : Sparsity, redundancy and robustness in artificial neural networks for learning and memory Type de document : Thèse/HDR Auteurs : Philippe Tigréat, Auteur ; Claude Berrou, Directeur de thèse Editeur : Institut Mines-Télécom Atlantique IMT Atlantique Année de publication : 2017 Autre Editeur : Université Bretagne Loire Importance : 150 P. Format : 21 x 30 cm Note générale : bibliographie
Thèse IMT Atlantique sous le sceau de l’Université Bretagne Loire pour obtenir le grade de Docteur, Signal, Image, VisionLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage (cognition)
[Termes IGN] apprentissage automatique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] codage
[Termes IGN] cognition
[Termes IGN] mémoire
[Termes IGN] reconnaissance de formes
[Termes IGN] stockage de donnéesIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The objective of research in Artificial Intelligence (AI) is to reproduce human cognitive abilities by means of modern computers. The results of the last few years seem to announce a technological revolution that could profoundly change society. We focus our interest on two fundamental cognitive aspects, learning and memory. Associative memories offer the possibility to store information elements and to retrieve them using a sub-part of their content, thus mimicking human memory. Deep Learning allows to transition from an analog perception of the outside world to a sparse and more compact representation.In Chapter 2, we present a neural associative memory model inspired by Willshaw networks, with constrained connectivity. This brings an performance improvement in message retrieval and a more efficient storage of information.In Chapter 3, a convolutional architecture was applied on a task of reading partially displayed words under similar conditions as in a former psychology study on human subjects. This experiment put inevidence the similarities in behavior of the network with the human subjects regarding various properties of the display of words.Chapter 4 introduces a new method for representing categories usingneuron assemblies in deep networks. For problems with a large number of classes, this allows to reduce significantly the dimensions of a network.Chapter 5 describes a method for interfacing deep unsupervised networks with clique-based associative memories. Note de contenu : 1- Introduction
2- Sparse Neural Associative Memories
3- Robustness of Deep Neural Networks to Erasures in a Reading Task
4- Assembly Output Codes for Learning Neural Networks
5- Combination of Unsupervised Learning and Associative Memory
6- Conclusion and OpeningsNuméro de notice : 25836 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Signal, Image, Vision : Mines-Télécom Atlantique : 2017 Organisme de stage : Laboratoire Labsticc nature-HAL : Thèse DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-01812053 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95178 SVM et réseaux neuronaux convolutifs pour la classification de scènes urbaines / Amaury Zarzelli (2017)
![]()
Titre : SVM et réseaux neuronaux convolutifs pour la classification de scènes urbaines Type de document : Mémoire Auteurs : Amaury Zarzelli, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2017 Importance : 42 p. Format : 21 x 30 cm Note générale : Bibliographie
Rapport de projet pluridisciplinaire, cycle Ingénieur 2e annéeLangues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] carte thématique
[Termes IGN] classification par réseau neuronal
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] image Streetview
[Termes IGN] Ottawa
[Termes IGN] régression
[Termes IGN] réseau neuronal convolutif
[Termes IGN] scène urbaineIndex. décimale : PROJET Mémoires : Rapports de projet - stage des ingénieurs de 2e année Résumé : (Auteur) L’accès de plus en plus répandu à des banques de données d’imagerie urbaine telles que StreetView de Google en corrélation avec le progrès des technologies en apprentissage machine facilite le développement de techniques permettant le traitement automatique des caractéristiques physiques du bâti sur de grandes zones urbaines. L’une des applications de ce traitement peut être l’étude sociologique, et notamment la mesure de la gentrification, processus par lequel des classes aisées s’installent dans des quartiers historiquement moins favorisés. En effet, ce phénomène se caractérise souvent par une modification de l’aspect des habitations, qui peut être détectée par un modèle de classification. Ce projet consiste à traiter toutes les étapes de cette classification, du téléchargement de l’imagerie urbaine jusqu’à la cartographie du phénomène étudié et peut être adapté à la qualification de n’importe quel phénomène urbain (accessibilité pour les piétons, structure des bâtiments…). Je me suis en particulier attaché à l’étape de la conception du modèle, en explorant notamment des techniques innovantes basées sur des réseaux de neurones convolutifs et dont les résultats sont prometteurs. Le travail a été effectué sur l’unité urbaine de la ville d’Ottawa au Canada. L’ensemble des travaux réalisés au cours du projet sont accessibles sur le dépôt GitHub suivant : https://github.com/azarz/gentriNet. Note de contenu : INTRODUCTION
1. Gestion de projet
2. Étapes de la classification
3. Résultats obtenus
CONCLUSIONNuméro de notice : 22806 Affiliation des auteurs : IGN (2012-2019) Thématique : IMAGERIE/INFORMATIQUE/MATHEMATIQUE/URBANISME Nature : Mémoire de projet pluridisciplinaire Organisme de stage : Université d’Ottawa Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88412 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 22806-01 PROJET Livre Centre de documentation Travaux d'élèves Disponible Documents numériques
peut être téléchargé
SVM et réseaux neuronaux convolutifsAdobe Acrobat PDF
Titre : Vision-based detection of aircrafts and UAVs Type de document : Thèse/HDR Auteurs : Artem Rozantsev, Auteur ; Pascal Fua, Directeur de thèse ; Vincent Lepetit, Directeur de thèse Editeur : Lausanne : Ecole Polytechnique Fédérale de Lausanne EPFL Année de publication : 2017 Importance : 117 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée à l'Ecole Polytechnique Fédérale de Lausanne pour l'obtention du grade de Docteur ès SciencesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Télédétection
[Termes IGN] apprentissage automatique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] cube espace-temps
[Termes IGN] détection d'objet
[Termes IGN] drone
[Termes IGN] image aérienne
[Termes IGN] objet mobile
[Termes IGN] régression
[Termes IGN] vision par ordinateurRésumé : (auteur) Unmanned Aerial Vehicles are becoming increasingly popular for a broad variety of tasks ranging from aerial imagery to objects delivery. With the expansion of the areas, where drones can be efficiently used, the collision risk with other flying objects increases. Avoiding such collisions would be a relatively easy task, if all the aircrafts in the neighboring airspace could communicate with each other and share their location information. However, it is often the case that either location information is unavailable (e.g. flying in GPS-denied environments) or communication is not possible (e.g. different communication channels or non-cooperative flight scenario). To ensure
flight safety in this kind of situations drones need a way to autonomously detect other objects that are intruding the neighboring airspace. Visual-based collision avoidance is of particular interest as cameras generally consume less power and are more lightweight than active sensor alternatives such as radars and lasers. We have therefore developed a set of increasingly sophisticated algorithms to provide drones with a visual collision avoidance capability. First, we present a novel method for detecting flying objects such as drones and planes that occupy a small part of the camera field of view, possibly move in front of complex backgrounds, and are filmed by a moving camera. In order to be solved this problem requires combining motion and appearance information, as neither of the two alone is capable of providing reliable
enough detections. We therefore propose a machine learning technique that operates on spatiotemporal cubes of image intensities where individual patches are aligned using an object-centric regression-based motion stabilization algorithm. Second, in order to reduce the need to collect a large training dataset and to manual annotate it, we introduce a way to generate realistic synthetic images. Given only a small set of real examples and a coarse 3D model of the object, synthetic data can be generated in arbitrary quantities and further used to supplement real examples for training a detector. The key ingredient of our method is that the synthetically generated images need to be as close as possible to the real ones not in terms of image quality, but according to the features, used by a machine learning algorithm. Third, though the aforementioned approach yields a substantial increase in performance when using Adaboost and DPM detectors, it does not generalize well to Convolutional Neural Networks, which have become the state-of-the-art. This happens because, as we add more and more synthetic data, the CNNs begin to overfit to the synthetic images at the expense of the real ones. We therefore propose a novel deep domain adaptation technique that allows efficiently combining real and synthetic images without overfitting to either of the two. While most of the adaptation techniques aim at learning features that are invariant to the possible difference of the images, coming from different sources (real and synthetic). Unlike those methods, we suggest modeling this difference with a special two-stream architecture. We evaluate our approach on three different
datasets and show its effectiveness for various classification and regression tasks.Note de contenu : Introduction
1- Flying Objects Detection
2- Synthetic Data Generation
3- Domain Adaption for Deep Networks
4- Concluding RemarksNuméro de notice : 25870 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Sciences : Lausanne : Suisse : 2017 En ligne : https://infoscience.epfl.ch/record/227934?ln=fr Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95538 Deep feature extraction and classification of hyperspectral images based on convolutional neural networks / Yushi Chen in IEEE Transactions on geoscience and remote sensing, vol 54 n° 10 (October 2016)
![]()
[article]
Titre : Deep feature extraction and classification of hyperspectral images based on convolutional neural networks Type de document : Article/Communication Auteurs : Yushi Chen, Auteur ; Hanlu Jiang, Auteur ; Chunyang Li, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 6232 - 6251 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal
[Termes IGN] détection de cible
[Termes IGN] filtrage numérique d'image
[Termes IGN] image hyperspectrale
[Termes IGN] régularisation de Tychonoff
[Termes IGN] réseau neuronal convolutifRésumé : (auteur) Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network (CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfitting in class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research. Numéro de notice : A2016-869 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2584107 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2584107 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83026
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 10 (October 2016) . - pp 6232 - 6251[article]Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning / Xiaorui Ma in ISPRS Journal of photogrammetry and remote sensing, vol 120 (october 2016)
![]()
[article]
Titre : Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning Type de document : Article/Communication Auteurs : Xiaorui Ma, Auteur ; Hongyu Wang, Auteur ; Jie Wang, Auteur Année de publication : 2016 Article en page(s) : pp 99 - 107 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] classification par réseau neuronal
[Termes IGN] classification semi-dirigée
[Termes IGN] image hyperspectrale
[Termes IGN] pondérationRésumé : (Auteur) Semisupervised learning is widely used in hyperspectral image classification to deal with the limited training samples, however, some more information of hyperspectral image should be further explored. In this paper, a novel semisupervised classification based on multi-decision labeling and deep feature learning is presented to exploit and utilize as much information as possible to realize the classification task. First, the proposed method takes two decisions to pre-label each unlabeled sample: local decision based on weighted neighborhood information is made by the surrounding samples, and global decision based on deep learning is performed by the most similar training samples. Then, some unlabeled ones with high confidence are selected to extent the training set. Finally, self decision, which depends on the self features exploited by deep learning, is employed on the updated training set to extract spectral-spatial features and produce classification map. Experimental results with real data indicate that it is an effective and promising semisupervised classification method for hyperspectral image. Numéro de notice : A2016-797 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.001 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.09.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82532
in ISPRS Journal of photogrammetry and remote sensing > vol 120 (october 2016) . - pp 99 - 107[article]Retrieval of leaf area index in different plant species using thermal hyperspectral data / Elnaz Neinavaz in ISPRS Journal of photogrammetry and remote sensing, vol 119 (September 2016)
PermalinkSea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: a case study / Lei Wang in IEEE Transactions on geoscience and remote sensing, vol 54 n° 8 (August 2016)
PermalinkObject-based image mapping of conifer tree mortality in San Diego county based on multitemporal aerial ortho-imagery / Mary Pyott Freeman in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 7 (juillet 2016)
PermalinkForest above ground biomass inversion by fusing GLAS with optical remote sensing data / Xiaohuan Xi in ISPRS International journal of geo-information, vol 5 n° 4 (April 2016)
PermalinkAutomatic selection of landmarks for navigation guidance / Rui Zhu in Transactions in GIS, vol 19 n° 2 (April 2015)
PermalinkPanorama sur les méthodes de classification des images satellites et techniques d'amélioration de la précision de la classification / O. El Kharki in Revue Française de Photogrammétrie et de Télédétection, n° 210 (Avril 2015)
PermalinkMODIS-based vegetation index has sufficient sensitivity to indicate stand-level intra-seasonal climatic stress in oak and beech forests / Tomáš Hlásny in Annals of Forest Science, vol 72 n° 1 (January 2015)
PermalinkClassification of submerged aquatic vegetation in Black River using hyperspectral image analysis / Roshan Pande-Chhetri in Geomatica, vol 68 n° 3 (September 2014)
PermalinkAn intelligent approach towards automatic shape modelling and object extraction from satellite images using cellular automata based algorithm / P. V. Arun in Geocarto international, vol 29 n° 5 - 6 (August - October 2014)
PermalinkAssessing the performance of two unsupervised dimensionality reduction techniques on hyperspectral APEX data for high resolution urban land-cover mapping / Luca Demarchi in ISPRS Journal of photogrammetry and remote sensing, vol 87 (January 2014)
PermalinkAssessing post-fire regeneration in a Mediterranean mixed forest using lidar data and artificial neural networks / Haifa Debouk in Photogrammetric Engineering & Remote Sensing, PERS, vol 79 n° 12 (December 2013)
PermalinkLa combinaison d'indicateurs de changement pour le suivi de l'évolution de l'occupation du sol à partir d'imagerie satellitale / Faten Katlane in Revue Française de Photogrammétrie et de Télédétection, n° 203 (Juillet 2013)
PermalinkMapping tropical forests and rubber plantations in complex landscapes by integrating PALSAR and MODIS imagery / J. Dong in ISPRS Journal of photogrammetry and remote sensing, vol 74 (Novembrer 2012)
PermalinkFusion of feature selection and optimized immune networks for hyperspectral image classification of urban landscapes / J. Im in Geocarto international, vol 27 n° 5 (August 2012)
PermalinkComparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points / Y. Shao in ISPRS Journal of photogrammetry and remote sensing, vol 70 (June 2012)
PermalinkEstimating tropical forest biomass with a combination of SAR image texture and Landsat TM data: An assessment of predictions between regions / M. Cutler in ISPRS Journal of photogrammetry and remote sensing, vol 70 (June 2012)
PermalinkAn assessment of internal neural network parameters affecting image classification accuracy / L. Zhou in Photogrammetric Engineering & Remote Sensing, PERS, vol 77 n° 12 (December 2011)
PermalinkObject-based image analysis of high-resolution satellite images using modified cloud basis function neural network and probabilistic relaxation labeling process / A. Rizvi in IEEE Transactions on geoscience and remote sensing, vol 49 n° 12 Tome 1 (December 2011)
PermalinkPixel unmixing in hyperspectral data by means of neural networks / Giorgio Licciardi in IEEE Transactions on geoscience and remote sensing, vol 49 n° 11 Tome 1 (November 2011)
PermalinkDevelopment of a modified neural network-based land cover classification system using automated data selector and multiresolution remotely sensed data / S. Khorram in Geocarto international, vol 26 n° 6 (October 2011)
Permalink