Descripteur
Termes IGN > informatique > intelligence artificielle > apprentissage automatique > apprentissage profond > réseau neuronal artificiel > Perceptron multicouche
Perceptron multicoucheSynonyme(s)MLP |
Documents disponibles dans cette catégorie (30)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Challenges in grassland mowing event detection with multimodal Sentinel images / Anatol Garioud (2019)
Titre : Challenges in grassland mowing event detection with multimodal Sentinel images Type de document : Article/Communication Auteurs : Anatol Garioud , Auteur ; Sébastien Giordano , Auteur ; Silvia Valero, Auteur ; Clément Mallet , Auteur Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN (2012-) Année de publication : 2019 Projets : 2-Pas d'info accessible - article non ouvert / Conférence : MultiTemp 2019, 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images 05/08/2019 07/08/2019 Shanghai Chine Proceedings IEEE Importance : pp 1 - 4 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] apprentissage profond
[Termes IGN] détection d'événement
[Termes IGN] données lidar
[Termes IGN] image multibande
[Termes IGN] image RapidEye
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] image TerraSAR-X
[Termes IGN] méthode robuste
[Termes IGN] nébulosité
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] Perceptron multicouche
[Termes IGN] prairie
[Termes IGN] régression
[Termes IGN] réseau neuronal récurrent
[Termes IGN] série temporelle
[Termes IGN] surveillance de la végétationRésumé : (auteur) Permanent Grasslands (PG) are heterogeneous environments with high spatial and temporal dynamics, subject to increasing environmental challenges. This study aims to identify requirements, key constraining factors and solutions for robust and complete detection of Mowing Events. Remote sensing is a powerful tool to monitor and investigate Near-Real-Time and seasonally PG cover. Here, pros and cons of Sentinel-2 (S2) and Sentinel-1 (S1) time series exploitation for Mowing Events (MowEve) detection are analysed. A deep-based approach is proposed to obtain consistent and homogeneous biophysical parameter times series for MowEve detection. Recurrent Neural Networks are proposed as regression strategy allowing the synergistic integration of optical and Synthetic Aperture Radar data to reconstruct dense NDVI times series. Experimental results corroborates the interest of deriving consistent and homogeneous series of biophysical parameters for subsequent MowEve detection. Numéro de notice : C2019-028 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Autre URL associée : vers HAL Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/Multi-Temp.2019.8866914 Date de publication en ligne : 29/11/2019 En ligne : https://doi.org/10.1109/Multi-Temp.2019.8866914 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94538
Titre : Foundations of deep convolutional models through kernel methods Type de document : Thèse/HDR Auteurs : Alberto Bietti, Auteur ; Julien Mairal, Directeur de thèse Editeur : Grenoble : Université de Grenoble Année de publication : 2019 Importance : 194 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse pour obtenir le grade de Docteur de la Communauté Université Grenoble Alpes, Spécialité : Mathématiques AppliquéesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage automatique
[Termes IGN] apprentissage profond
[Termes IGN] approche hiérarchique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] espace de Hilbert
[Termes IGN] état de l'art
[Termes IGN] invariance
[Termes IGN] jeu de données
[Termes IGN] méthode fondée sur le noyau
[Termes IGN] optimisation (mathématiques)
[Termes IGN] Perceptron multicoucheIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The increased availability of large amounts of data, from images in social networks, speech waveforms from mobile devices, and large text corpuses, to genomic and medical data, has led to a surge of machine learning techniques. Such methods exploit statistical patterns in these large datasets for making accurate predictions on new data. In recent years, deep learning systems have emerged as a remarkably successful class of machine learning algorithms, which rely on gradient-based methods for training multi-layer models that process data in a hierarchical manner. These methods have been particularly successful in tasks where the data consists of natural signals such as images or audio; this includes visual recognition, object detection or segmentation, and speech recognition.For such tasks, deep learning methods often yield the best known empirical performance; yet, the high dimensionality of the data and large number of parameters of these models make them challenging to understand theoretically. Their success is often attributed in part to their ability to exploit useful structure in natural signals, such as local stationarity or invariance, for instance through choices of network architectures with convolution and pooling operations. However, such properties are still poorly understood from a theoretical standpoint, leading to a growing gap between the theory and practice of machine learning. This thesis is aimed towards bridging this gap, by studying spaces of functions which arise from given network architectures, with a focus on the convolutional case. Our study relies on kernel methods, by considering reproducing kernel Hilbert spaces (RKHSs) associated to certain kernels that are constructed hierarchically based on a given architecture. This allows us to precisely study smoothness, invariance, stability to deformations, and approximation properties of functions in the RKHS. These representation properties are also linked with optimization questions when training deep networks with gradient methods in some over-parameterized regimes where such kernels arise. They also suggest new practical regularization strategies for obtaining better generalization performance on small datasets, and state-of-the-art performance for adversarial robustness on image tasks. Note de contenu : 1- Introduction
2- Invariance, Stability to deformations, and complexity of deep convolutional representations
3- A kernel perspective on regularization and robustness of deep neural networks
4- Links with optimization: inductive bias of neural tangent kernels
5- Invariance and stability through regularization: a stochastic optimization algorithm for data augmentation
6- Conclusion and perspectivesNuméro de notice : 25833 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Mathématiques Appliquées : Grenoble Alpes : 2019 nature-HAL : Thèse DOI : sans En ligne : https://hal.archives-ouvertes.fr/tel-02543073/ document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95171 Designing an integrated urban growth prediction model: a scenario-based approach for preserving scenic landscapes / Sepideh Saeidi in Geocarto international, vol 33 n° 12 (December 2018)
[article]
Titre : Designing an integrated urban growth prediction model: a scenario-based approach for preserving scenic landscapes Type de document : Article/Communication Auteurs : Sepideh Saeidi, Auteur ; Seyed Hamed Mirkarimi, Auteur ; Marjan Mohammadzadeh, Auteur ; Abdolrassoul Salmanmahiny, Auteur ; Colin Arrowsmith, Auteur Année de publication : 2018 Article en page(s) : pp 1381 - 1397 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] automate cellulaire
[Termes IGN] croissance urbaine
[Termes IGN] Iran
[Termes IGN] méthode d'étalonnage basée sur le modèle
[Termes IGN] modèle de simulation
[Termes IGN] occupation du sol
[Termes IGN] paysage urbain
[Termes IGN] Perceptron multicouche
[Termes IGN] réseau neuronal artificielRésumé : (auteur) This study demonstrates the integration of landscape aesthetic quality and probable urban growth patterns in urban landscape modelling. This was performed using SLEUTH as a scenario-based urban growth model in Gorgan City of Iran. Future urbanization was predicted under developing three different scenarios including historical, managed and aesthetically sound urban growth up to the year 2030. Multi-Layer Perceptron neural network model was conducted for mapping the aesthetic suitability of the study area. The aesthetic suitability layer was used in the third scenario of SLEUTH model as the excluded layer to protect the scenic patches in future. The results showed that by correct implementation of urban growth policies, 323 ha in the second scenario and 650 ha in the third scenario would be saved. This integrated model would help the planners for a better management of urban landscapes as a Spatial Decision Support System. Numéro de notice : A2019-050 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2017.1353647 Date de publication en ligne : 24/07/2017 En ligne : https://doi.org/10.1080/10106049.2017.1353647 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92071
in Geocarto international > vol 33 n° 12 (December 2018) . - pp 1381 - 1397[article]A deep neural network with spatial pooling (DNNSP) for 3-D point cloud classification / Zhen Wang in IEEE Transactions on geoscience and remote sensing, vol 56 n° 8 (August 2018)
[article]
Titre : A deep neural network with spatial pooling (DNNSP) for 3-D point cloud classification Type de document : Article/Communication Auteurs : Zhen Wang, Auteur ; Liqiang Zhang, Auteur ; Liang Zhang, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 4594 - 4604 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] apprentissage profond
[Termes IGN] arbre aléatoire
[Termes IGN] classification par réseau neuronal
[Termes IGN] données hétérogènes
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] méthode robuste
[Termes IGN] Perceptron multicouche
[Termes IGN] pondération
[Termes IGN] précision de la classification
[Termes IGN] scène urbaine
[Termes IGN] semis de pointsMots-clés libres : deep neural network with spatial pooling (DNNSP) Résumé : (Auteur) The large number of object categories and many overlapping or closely neighboring objects in large-scale urban scenes pose great challenges in point cloud classification. Most works in deep learning have achieved a great success on regular input representations, but they are hard to be directly applied to classify point clouds due to the irregularity and inhomogeneity of the data. In this paper, a deep neural network with spatial pooling (DNNSP) is proposed to classify large-scale point clouds without rasterization. The DNNSP first obtains the point-based feature descriptors of all points in each point cluster. The distance minimum spanning tree-based pooling is then applied in the point feature representation to describe the spatial information among the points in the point clusters. The max pooling is next employed to aggregate the point-based features into the cluster-based features. To assure the DNNSP is invariant to the point permutation and sizes of the point clusters, the point-based feature representation is determined by the multilayer perception (MLP) and the weight sharing for each point is retained, which means that the weight of each point in the same layer is the same. In this way, the DNNSP can learn the features of points scaled from the entire regions to the centers of the point clusters, which makes the point cluster-based feature representations robust and discriminative. Finally, the cluster-based features are input to another MLP for point cloud classification. We have evaluated qualitatively and quantitatively the proposed method using several airborne laser scanning and terrestrial laser scanning point cloud data sets. The experimental results have demonstrated the effectiveness of our method in improving classification accuracy. Numéro de notice : A2018-471 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2829625 Date de publication en ligne : 22/05/2018 En ligne : https://doi.org/10.1109/TGRS.2018.2829625 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91253
in IEEE Transactions on geoscience and remote sensing > vol 56 n° 8 (August 2018) . - pp 4594 - 4604[article]
Titre : Introduction to Deep Learning : From Logical Calculus to Artificial Intelligence Type de document : Monographie Auteurs : Sandro Skansi, Auteur Editeur : Springer Nature Année de publication : 2018 Importance : 196 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-319-73004-2 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage profond
[Termes IGN] classification
[Termes IGN] codage
[Termes IGN] estimation par noyau
[Termes IGN] matrice de covariance
[Termes IGN] Perceptron multicouche
[Termes IGN] Python (langage de programmation)
[Termes IGN] régression logistique
[Termes IGN] réseau neuronal artificiel
[Termes IGN] réseau neuronal convolutif
[Termes IGN] sciences cognitives
[Termes IGN] théorie des probabilitésRésumé : (auteur) This textbook presents a concise, accessible and engaging first introduction to deep learning, offering a wide range of connectionist models which represent the current state-of-the-art. The text explores the most popular algorithms and architectures in a simple and intuitive style, explaining the mathematical derivations in a step-by-step manner. The content coverage includes convolutional networks, LSTMs, Word2vec, RBMs, DBNs, neural Turing machines, memory networks and autoencoders. Numerous examples in working Python code are provided throughout the book, and the code is also supplied separately at an accompanying website.
Topics and features:
Introduces the fundamentals of machine learning, and the mathematical and computational prerequisites for deep learning
Discusses feed-forward neural networks, and explores the modifications to these which can be applied to any neural network
Examines convolutional neural networks, and the recurrent connections to a feed-forward neural network
Describes the notion of distributed representations, the concept of the autoencoder, and the ideas behind language processing with deep learning
Presents a brief history of artificial intelligence and neural networks, and reviews interesting
open research problems in deep learning and connectionism
This clearly written and lively primer on deep learning is essential reading for graduate and advanced undergraduate students of computer science, cognitive science and mathematics, as well as fields such as linguistics, logic, philosophy, and psychology.Note de contenu : 1- From Logic to Cognitive Science
2- Mathematical and Computational Prerequisites
3- Machine Learning Basics
4- Feedforward Neural Networks
5- Modifications and Extensions to a Feed-Forward Neural Network
6- Convolutional Neural Networks
7- Recurrent Neural Networks
8- Autoencoders
9- Neural Language Models
10- An Overview of Different Neural Network Architectures
11- ConclusionNuméro de notice : 25787 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Monographie En ligne : https://doi.org/10.1007/978-3-319-73004-2 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94990 Multilayer projective dictionary pair learning and sparse autoencoder for PolSAR image classification / Yanqiao Chen in IEEE Transactions on geoscience and remote sensing, vol 55 n° 12 (December 2017)PermalinkAtmospheric correction over coastal waters using multilayer neural networks / Yongzhen Fan in Remote sensing of environment, vol 199 (15 September 2017)PermalinkA relative evaluation of random forests for land cover mapping in an urban area / Di Shi in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 8 (August 2017)PermalinkPermalinkRéseaux de neurones convolutifs pour la segmentation sémantique et l'apprentissage d'invariants de couleur / Damien Fourure (2017)PermalinkEstimation of forest biomass using multivariate relevance vector regression / Alireza Sharifi in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 1 (January 2016)PermalinkPerformance analysis of radial basis function networks and multi-layer perceptron networks in modeling urban change: a case study / Hossein Shafizadeh-Moghadam in International journal of geographical information science IJGIS, vol 29 n° 4 (April 2015)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)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)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)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)PermalinkSimilarity weighted instance-based learning for the generation of transition potentials in land use change modeling / F. Sangermano in Transactions in GIS, vol 14 n° 5 (October 2010)PermalinkPotentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes / Konstantinos Topouzelis in Geocarto international, vol 24 n° 3 (June - July 2009)PermalinkArtificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland / S. Chattopadhyay in International Journal of Remote Sensing IJRS, vol 28 n°19-20 (October 2007)PermalinkMultispectral image classification: a supervised neural computation approach based on rough-fuzzy membership function and weak fuzzy similarity relation / A. Agrawal in International Journal of Remote Sensing IJRS, vol 28 n°19-20 (October 2007)PermalinkArtificial neural networks for mapping regional-scale upland vegetation from high spatial resolution imagery / H. Mills in International Journal of Remote Sensing IJRS, vol 27 n° 11 (June 2006)PermalinkRobust multiple estimator systems for the analysis of biophysical parameters from remotely sensed data / Lorenzo Bruzzone in IEEE Transactions on geoscience and remote sensing, vol 43 n° 1 (January 2005)PermalinkA cognitive pyramid for contextual classification of remote sensing images / E. Binaghi in IEEE Transactions on geoscience and remote sensing, vol 41 n° 12 (December 2003)PermalinkA neural adaptive model for feature extraction and recognition in high resolution remote sensing imagery / E. Binaghi in International Journal of Remote Sensing IJRS, vol 24 n° 20 (October 2003)Permalink