Centre dedocumentation
scientifique

Advances and applications in deep learning / Marco Antonio Aceves-Fernandez (2020)  

Public Titre : Advances and applications in deep learning Type de document : Monographie Auteurs : Marco Antonio Aceves-Fernandez, Editeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2020 Importance : 122 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-1-83962-879-5 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] apprentissage automatique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] constante diélectrique [Termes IGN] méthode fondée sur le noyau [Termes IGN] programmation stochastique [Termes IGN] temps réel [Termes IGN] vision par ordinateur Résumé : (auteur) Artificial Intelligence (AI) has attracted the attention of researchers and users alike and is taking an increasingly crucial role in our modern society. From cars, smartphones, and airplanes to medical equipment, consumer applications, and industrial machines, the impact of AI is notoriously changing the world we live in. In this context, Deep Learning (DL) is one of the techniques that has taken the lead for cognitive processes, pattern recognition, object detection, and machine learning, all of which have played a crucial role in the growth of AI. As such, this book examines DL applications and future trends in the field. It is a useful resource for researchers and students alike. Note de contenu : 1- Advancements in deep learning theory and applications: Perspective in 2020 and beyond 2- Advances in convolutional neural networks 3- Transfer learning and deep domain adaptation 4- Deep learning enabled nanophotonics 5- Explainable artificial intelligence (xAI) approaches and deep meta-learning models 6- Dynamic decision-making for stabilized deep learning software platforms Numéro de notice : 28565 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Recueil / ouvrage collectif DOI : 10.5772/intechopen.87786 En ligne : https://doi.org/10.5772/intechopen.87786 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97647

SpiNNaker: A spiking neural network architecture / Steve Furber (2020)  

Public Titre : SpiNNaker: A spiking neural network architecture Type de document : Monographie Auteurs : Steve Furber, Editeur scientifique ; Petrut Bogdan, Editeur scientifique Editeur : Boston, Delft : Now publishers Année de publication : 2020 Importance : 352 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-1-68083-652-3 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] apprentissage profond [Termes IGN] Cerveau [Termes IGN] outil logiciel [Termes IGN] programmation stochastique [Termes IGN] puce [Termes IGN] réseau neuronal convolutif [Termes IGN] système de traitement de l'information [Termes IGN] vision par ordinateur Résumé : (éditeur) 20 years in conception and 15 in construction, the SpiNNaker project has delivered the world’s largest neuromorphic computing platform incorporating over a million ARM mobile phone processors and capable of modelling spiking neural networks of the scale of a mouse brain in biological real time. This machine, hosted at the University of Manchester in the UK, is freely available under the auspices of the EU Flagship Human Brain Project. This book tells the story of the origins of the machine, its development and its deployment, and the immense software development effort that has gone into making it openly available and accessible to researchers and students the world over. It also presents exemplar applications from ‘Talk’, a SpiNNaker-controlled robotic exhibit at the Manchester Art Gallery as part of ‘The Imitation Game’, a set of works commissioned in 2016 in honour of Alan Turing, through to a way to solve hard computing problems using stochastic neural networks. The book concludes with a look to the future, and the SpiNNaker-2 machine which is yet to come. Note de contenu : 1- Origins 2- The SpiNNaker Chip 3- Building SpiNNaker Machines 4- Stacks of Software Stacks 5- Applications - Doing Stuff on the Machine 6- From Activations to Spikes 7- Learning in Neural Networks 8- Creating the Future Numéro de notice : 25978 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Monographie DOI : 10.1561/9781680836523 En ligne : http://dx.doi.org/10.1561/9781680836523 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96705

Optimization in control applications / Guillermo Valencia-Palomo (2019)  

Public Titre : Optimization in control applications Type de document : Monographie Auteurs : Guillermo Valencia-Palomo, Editeur scientifique ; Francisco Ronay Lopez-Estrada, Editeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2019 Importance : 256 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-3-03897-448-2 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Mathématique [Termes IGN] modèle mathématique [Termes IGN] optimisation (mathématiques) [Termes IGN] programmation stochastique Résumé : (auteur) Mathematical optimization is the selection of the best element in a set with respect to a given criterion. Optimization has become one of the most-used tools in modern control theory for computing the control law, adjusting the controller parameters (tuning), model fitting, and finding suitable conditions in order to fulfill a given closed-loop property, among others. In the simplest case, optimization consists of maximizing or minimizing a function by systematically choosing input values from a valid input set and computing the function value. Nevertheless, real-world control systems need to comply with several conditions and constraints that have to be taken into account in the problem formulation—these represent challenges in the application of the optimization algorithms.The aim of this Special Issue is to offer the state-of-the-art of the most advanced optimization techniques (online and offline) and their applications in control engineering.] Note de contenu : 1- Rapid solution of optimal control problems by a functional spreadsheet paradigm: A practical method for the non-programme 2- Novel spreadsheet direct method for optimal control problems 3- Time needed to control an epidemic with restricted resources in SIR model with short-term controlled population: A fixed point method for a free isoperimetric optimal control problem 4- Optimal strategies for psoriasis treatment 5- Optimal control analysis of a mathematical model for breast cancer 6- Cost-effective analysis of control strategies to reduce the prevalence of cutaneous leishmaniasis, based on a mathematical model 7- Optimal control and computational method for the resolution of isoperimetric problem in a discrete-time SIRS system 8- Solution of optimal harvesting problem by finite difference approximations of size-structured population model 9- Solution of fuzzy differential equations using fuzzy Sumudu transforms 10- A simple spectral observer 11- Differential evolution algorithm for multilevel assignment problem: A case study in chicken transportation 12- Modeling and simulation of a hydraulic network for leak diagnosis Numéro de notice : 28503 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Monographie DOI : 10.3390/books978-3-03897-448-2 En ligne : https://doi.org/10.3390/books978-3-03897-448-2 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97002

Human mobility semantics analysis : a probabilistic and scalable approach / Xiaohui Guo in Geoinformatica [en ligne], vol 22 n° 3 (July 2018)  

Public [article]  inGeoinformatica [en ligne] > vol 22 n° 3 (July 2018) . - pp 507 - 539 Titre : Human mobility semantics analysis : a probabilistic and scalable approach Type de document : Article/Communication Auteurs : Xiaohui Guo, Auteur ; Richong Zhang, Auteur ; Xudong Liu, Auteur ; Jinpeng Huai, Auteur Année de publication : 2018 Article en page(s) : pp 507 - 539 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse sémantique [Termes IGN] données localisées [Termes IGN] données spatiotemporelles [Termes IGN] mobilité [Termes IGN] programmation stochastique [Termes IGN] trace numérique Résumé : (Auteur) The popularity of smart mobile devices generated data, e.g., check-ins and geo-tagged status, offers new opportunity for better understanding human mobility regularity. Existing works on this problem usually resort to explicit frequency statistics models, such as association rules and sequential patterns, and rely on Euclidean distance to measure the spatial dependence. However, the noisiness and uncertainty natures of geospatial data hinder these methods’ application on human mobility in robust and intuitive way. Moreover, the mobility spatial data volume and accumulation speed challenge the traditional methods in efficiency, scalability, and time-space complexity aspects. In this context, we leverage full Bayesian sequential modeling, to revisit mobility regularity discovery from high level probabilistic semantic knowledge perspective, and to alleviate the inherent in mobility modeling and geo-data noisiness induced uncertainty. Specifically, the mobility semantics is embodied by virtue of underlying geospatial topics and topical transitions of mobility trajectories. A classic variational inference is derived to estimate posterior and predictive probabilities, and furthermore, the stochastic optimization is utilized to mitigate the costly computational overhead in message passing subroutine. The experimental results confirm that our approach not only reasonably recognizes the geospatial mobility semantic patterns, but also scales up well to embrace the massive spatial-temporal human mobility activity data. Numéro de notice : A2018-310 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10707-017-0295-0 date de publication en ligne : 10/04/2017 En ligne : https://doi.org/10.1007/s10707-017-0295-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90757 [article]

Determining the appropriate timing of the next forest inventory: incorporating forest owner risk preferences and the uncertainty of forest data quality / Kyle J. Eyvindson in Annals of Forest Science [en ligne], vol 74 n° 1 (March 2017)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 74 n° 1 (March 2017) Titre : Determining the appropriate timing of the next forest inventory: incorporating forest owner risk preferences and the uncertainty of forest data quality Type de document : Article/Communication Auteurs : Kyle J. Eyvindson, Auteur ; Aaron D. Petty, Auteur ; Annika S. Kangas, Auteur Année de publication : 2017 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] aide à la décision [Termes IGN] incertitude des données [Termes IGN] méthode de Monte-Carlo [Termes IGN] programmation stochastique [Termes IGN] risque naturel [Termes IGN] simulation numérique [Vedettes matières IGN] Inventaire forestier Résumé : (Auteur) The timing to conduct new forest inventories should be based on the requirements of the decision maker. Importance should be placed on the objectives of the decision maker and his/her risk preferences related to those objectives. Context : The appropriate use of pertinent and available information is paramount in any decision-making process. Within forestry, a new forest inventory is typically conducted prior to creating a forest management plan. The acquisition of new forest inventory data is justified by the simple statement of “good decisions require good data.” Aims : By integrating potential risk preferences, we examine the specific needs to collect new forest information. Methods : Through a two-stage stochastic programming with recourse model, we evaluate the specific timing to conduct a holding level forest inventory. A Monte Carlo simulation was used to integrate both inventory and growth model errors, resulting in a large number of potential scenarios process to be used as data for the stochastic program. To allow for recourse, an algorithm to sort the simulations to represent possible updated forest inventories, using the same data was developed. Results : Risk neutral decision makers should delay obtaining new forest information when compared to risk averse decision makers. Conclusion : New inventory data may only need to be collected rather infrequently; however, the exact timing depends on the forest owner’s objectives and risk preferences. Numéro de notice : A2017-042 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1007/s13595-016-0607-9 date de publication en ligne : 08/02/2017 En ligne : https://doi.org/10.1007/s13595-016-0607-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84200 [article]

Integrating risk preferences in forest harvest scheduling / Kyle J. Eyvindson in Annals of Forest Science [en ligne], vol 73 n° 2 (June 2016)  

Permalink

Stochastic dynamic programming / Kjetil Kåre Haugen (2016)  

Permalink

A stochastic method for the generation of optimized building-layouts respecting urban regulation / Shuang He (oct 2014)  

Permalink

LIBRJMCMC: an open-source generic C++ library for stochastic optimization / Mathieu Brédif (2012)  

Permalink

Global optimization of core station networks for space geodesy: application to the referencing of the SLR EOP with respect to ITRF / David Coulot in Journal of geodesy, vol 84 n° 1 (January 2010)  

Permalink

A geometric stochastic approach based on marked point processes for road mark detection from high resolution aerial images / Olivier Tournaire in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 6 (November - December 2009)  

Permalink

A new computationally efficient stochastic approach for building reconstruction from satellite data / Florent Lafarge (01/07/2008) 

Permalink

Kalman filtering, theory and practice using MATLAB, [Third edition] / Mohinder S. Grewal (2008)

Permalink

Analyse und Optimierung geodätischer Messanordnungen unter besonderer Berücksichtigung des Intervallansatzes / S. Schön (2003)

Permalink

Introduction à l'optimisation / J.C. Culioli (1994)

Permalink