Academic literature on the topic 'Réseaux de neurones LSTM'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Réseaux de neurones LSTM.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Réseaux de neurones LSTM"
HARINAIVO, A., H. HAUDUC, and I. TAKACS. "Anticiper l’impact de la météo sur l’influent des stations d’épuration grâce à l’intelligence artificielle." Techniques Sciences Méthodes 3 (March 20, 2023): 33–42. http://dx.doi.org/10.36904/202303033.
Full textOthmani-Guibourg, Mehdi William, Amal El Fallah Seghrouchni, and Jean-Loup Farges. "LSTM Path-Maker : une stratégie à base de réseau de neurones LSTM pour la patrouille multiagent." Revue Ouverte d'Intelligence Artificielle 3, no. 3-4 (April 8, 2022): 345–72. http://dx.doi.org/10.5802/roia.34.
Full text-BORNE, Pierre. "Les réseaux de neurones." Revue de l'Electricité et de l'Electronique -, no. 08 (2006): 31. http://dx.doi.org/10.3845/ree.2006.074.
Full text-BORNE, Pierre. "Les réseaux de neurones." Revue de l'Electricité et de l'Electronique -, no. 08 (2006): 37. http://dx.doi.org/10.3845/ree.2006.075.
Full text-Y. HAGGEGE, Joseph. "Les réseaux de neurones." Revue de l'Electricité et de l'Electronique -, no. 08 (2006): 43. http://dx.doi.org/10.3845/ree.2006.076.
Full text-BENREJEB, Mohamed. "Les réseaux de neurones." Revue de l'Electricité et de l'Electronique -, no. 08 (2006): 47. http://dx.doi.org/10.3845/ree.2006.077.
Full text-Y. HAGGEGE, Joseph. "Les réseaux de neurones." Revue de l'Electricité et de l'Electronique -, no. 08 (2006): 50. http://dx.doi.org/10.3845/ree.2006.078.
Full text-BENREJEB, Mohamed. "Les réseaux de neurones." Revue de l'Electricité et de l'Electronique -, no. 08 (2006): 55. http://dx.doi.org/10.3845/ree.2006.079.
Full textBélanger, M., N. El-Jabi, D. Caissie, F. Ashkar, and J. M. Ribi. "Estimation de la température de l'eau de rivière en utilisant les réseaux de neurones et la régression linéaire multiple." Revue des sciences de l'eau 18, no. 3 (April 12, 2005): 403–21. http://dx.doi.org/10.7202/705565ar.
Full textMézard, Marc, and Jean-Pierre Nadal. "Réseaux de neurones et physique statistique." Intellectica. Revue de l'Association pour la Recherche Cognitive 9, no. 1 (1990): 213–45. http://dx.doi.org/10.3406/intel.1990.884.
Full textDissertations / Theses on the topic "Réseaux de neurones LSTM"
Gelly, Grégory. "Réseaux de neurones récurrents pour le traitement automatique de la parole." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLS295/document.
Full textAutomatic speech processing is an active field of research since the 1950s. Within this field the main area of research is automatic speech recognition but simpler tasks such as speech activity detection, language identification or speaker identification are also of great interest to the community. The most recent breakthrough in speech processing appeared around 2010 when speech recognition systems using deep neural networks drastically improved the state-of-the-art. Inspired by this gains and the work of Alex Graves on recurrent neural networks (RNN), we decided to explore the possibilities brought by these models on realistic data for two different tasks: speech activity detection and spoken language identification. In this work, we closely look at a specific model for the RNNs: the Long Short Term Memory (LSTM) which mitigates a lot of the difficulties that can arise when training an RNN. We augment this model and introduce optimization methods that lead to significant performance gains for speech activity detection and language identification. More specifically, we introduce a WER-like loss function to train a speech activity detection system so as to minimize the word error rate of a downstream speech recognition system. We also introduce two different methods to successfully train a multiclass classifier based on neural networks for tasks such as LID. The first one is based on a divide-and-conquer approach and the second one is based on an angular proximity loss function. Both yield performance gains but also speed up the training process
Stuner, Bruno. "Cohorte de réseaux de neurones récurrents pour la reconnaissance de l'écriture." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMR024.
Full textState-of-the-art methods for handwriting recognition are based on LSTM recurrent neural networks (RNN) which achieve high performance recognition. In this thesis, we propose the lexicon verification and the cohort generation as two new building blocs to tackle the problem of handwriting recognition which are : i) the large vocabulary problem and the use of lexicon driven methods ii) the combination of multiple optical models iii) the need for large labeled dataset for training RNN. The lexicon verification is an alternative to the lexicon driven decoding process and can deal with lexicons of 3 millions words. The cohort generation is a method to get easily and quickly a large number of complementary recurrent neural networks extracted from a single training. From these two new techniques we build and propose a new cascade scheme for isolated word recognition, a new line level combination LV-ROVER and a new self-training strategy to train LSTM RNN for isolated handwritten words recognition. The proposed cascade combines thousands of LSTM RNN with lexicon verification and achieves state-of-the art word recognition performance on the Rimes and IAM datasets. The Lexicon Verified ROVER : LV-ROVER, has a reduce complexity compare to the original ROVER algorithm and combine hundreds of recognizers without language models while achieving state of the art for handwritten line text on the RIMES dataset. Our self-training strategy use both labeled and unlabeled data with the unlabeled data being self-labeled by its own lexicon verified predictions. The strategy enables self-training with a single BLSTM and show excellent results on the Rimes and Iam datasets
Bouaziz, Mohamed. "Réseaux de neurones récurrents pour la classification de séquences dans des flux audiovisuels parallèles." Thesis, Avignon, 2017. http://www.theses.fr/2017AVIG0224/document.
Full textIn the same way as TV channels, data streams are represented as a sequence of successive events that can exhibit chronological relations (e.g. a series of programs, scenes, etc.). For a targeted channel, broadcast programming follows the rules defined by the channel itself, but can also be affected by the programming of competing ones. In such conditions, event sequences of parallel streams could provide additional knowledge about the events of a particular stream. In the sphere of machine learning, various methods that are suited for processing sequential data have been proposed. Long Short-Term Memory (LSTM) Recurrent Neural Networks have proven its worth in many applications dealing with this type of data. Nevertheless, these approaches are designed to handle only a single input sequence at a time. The main contribution of this thesis is about developing approaches that jointly process sequential data derived from multiple parallel streams. The application task of our work, carried out in collaboration with the computer science laboratory of Avignon (LIA) and the EDD company, seeks to predict the genre of a telecast. This prediction can be based on the histories of previous telecast genres in the same channel but also on those belonging to other parallel channels. We propose a telecast genre taxonomy adapted to such automatic processes as well as a dataset containing the parallel history sequences of 4 French TV channels. Two original methods are proposed in this work in order to take into account parallel stream sequences. The first one, namely the Parallel LSTM (PLSTM) architecture, is an extension of the LSTM model. PLSTM simultaneously processes each sequence in a separate recurrent layer and sums the outputs of each of these layers to produce the final output. The second approach, called MSE-SVM, takes advantage of both LSTM and Support Vector Machines (SVM) methods. Firstly, latent feature vectors are independently generated for each input stream, using the output event of the main one. These new representations are then merged and fed to an SVM algorithm. The PLSTM and MSE-SVM approaches proved their ability to integrate parallel sequences by outperforming, respectively, the LSTM and SVM models that only take into account the sequences of the main stream. The two proposed approaches take profit of the information contained in long sequences. However, they have difficulties to deal with short ones. Though MSE-SVM generally outperforms the PLSTM approach, the problem experienced with short sequences is more pronounced for MSE-SVM. Finally, we propose to extend this approach by feeding additional information related to each event in the input sequences (e.g. the weekday of a telecast). This extension, named AMSE-SVM, has a remarkably better behavior with short sequences without affecting the performance when processing long ones
Chraibi, Kaadoud Ikram. "apprentissage de séquences et extraction de règles de réseaux récurrents : application au traçage de schémas techniques." Thesis, Bordeaux, 2018. http://www.theses.fr/2018BORD0032/document.
Full textThere are two important aspects of the knowledge that an individual acquires through experience. One corresponds to the semantic memory (explicit knowledge, such as the learning of concepts and categories describing the objects of the world) and the other, the procedural or syntactic memory (knowledge relating to the learning of rules or syntax). This "syntactic memory" is built from experience and particularly from the observation of sequences of objects whose organization obeys syntactic rules.It must have the capability to aid recognizing as well as generating valid sequences in the future, i.e., sequences respecting the learnt rules. This production of valid sequences can be done either in an explicit way, that is, by evoking the underlying rules, or implicitly, when the learning phase has made it possible to capture the principle of organization of the sequences without explicit recourse to the rules. Although the latter is faster, more robust and less expensive in terms of cognitive load as compared to explicit reasoning, the implicit process has the disadvantage of not giving access to the rules and thus becoming less flexible and less explicable. These mnemonic mechanisms can also be applied to business expertise. The capitalization of information and knowledge in general, for any company is a major issue and concerns both the explicit and implicit knowledge. At first, the expert makes a choice to explicitly follow the rules of the trade. But then, by dint of repetition, the choice is made automatically, without explicit evocation of the underlying rules. This change in encoding rules in an individual in general and particularly in a business expert can be problematic when it is necessary to explain or transmit his or her knowledge. Indeed, if the business concepts can be formalized, it is usually in any other way for the expertise which is more difficult to extract and transmit.In our work, we endeavor to observe sequences of electrical components and in particular the problem of extracting rules hidden in these sequences, which are an important aspect of the extraction of business expertise from technical drawings. We place ourselves in the connectionist domain, and we have particularly considered neuronal models capable of processing sequences. We implemented two recurrent neural networks: the Elman model and a model with LSTM (Long Short Term Memory) units. We have evaluated these two models on different artificial grammars (Reber's grammar and its variations) in terms of learning, their generalization abilities and their management of sequential dependencies. Finally, we have also shown that it is possible to extract the encoded rules (from the sequences) in the recurrent network with LSTM units, in the form of an automaton. The electrical domain is particularly relevant for this problem. It is more constrained with a limited combinatorics than the planning of tasks in general cases like navigation for example, which could constitute a perspective of this work
Adam, Chloé. "Pattern Recognition in the Usage Sequences of Medical Apps." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLC027/document.
Full textRadiologists use medical imaging solutions on a daily basis for diagnosis. Improving user experience is a major line of the continuous effort to enhance the global quality and usability of software products. Monitoring applications enable to record the evolution of various software and system parameters during their use and in particular the successive actions performed by the users in the software interface. These interactions may be represented as sequences of actions. Based on this data, this work deals with two industrial topics: software crashes and software usability. Both topics imply on one hand understanding the patterns of use, and on the other developing prediction tools either to anticipate crashes or to dynamically adapt software interface according to users' needs. First, we aim at identifying crash root causes. It is essential in order to fix the original defects. For this purpose, we propose to use a binomial test to determine which type of patterns is the most appropriate to represent crash signatures. The improvement of software usability through customization and adaptation of systems to each user's specific needs requires a very good knowledge of how users use the software. In order to highlight the trends of use, we propose to group similar sessions into clusters. We compare 3 session representations as inputs of different clustering algorithms. The second contribution of our thesis concerns the dynamical monitoring of software use. We propose two methods -- based on different representations of input actions -- to address two distinct industrial issues: next action prediction and software crash risk detection. Both methodologies take advantage of the recurrent structure of LSTM neural networks to capture dependencies among our sequential data as well as their capacity to potentially handle different types of input representations for the same data
Hambarek, Djamel Eddine. "Développement d'une méthodologie d'essais dynamiques appliquée à la mise au point moteur." Electronic Thesis or Diss., Ecole centrale de Nantes, 2023. http://www.theses.fr/2023ECDN0035.
Full textThe work of this thesis responds to the context of the evolution of engine depollution norms together with the increase of the clientrequirements. It proposes a complete methodology of engine calibration considering dynamic effects with the aim of an efficient control in terms of emissions and performances. The method is divided into four steps: the dynamic design of experiments generating a set of RDE (Real Driving Emissions) cycles and dynamic variations of engine parameters using low discrepancy sequences: test results are used to train a dynamical model using LSTM neural network to predict output dynamic variations(CO, HC, NOx, Exhaust flow and temperature). The trained model is used in an optimization loop to calibrate the engine parameters using a genetic algorithm. The catalyst warm-up phase is the chosen phase for the development of the method. It is the phase occuring from engine start until the catalyst is the most efficient. It is indeed the phase with the most important emissions which is coherent with the aim of the engine calibration. The results showed noticeable improvements of CO, HC and Nox reduction compared to the steady state (baseline) method
Wenzek, Didier. "Construction de réseaux de neurones." Phd thesis, Grenoble INPG, 1993. http://tel.archives-ouvertes.fr/tel-00343569.
Full textTsopze, Norbert. "Treillis de Galois et réseaux de neurones : une approche constructive d'architecture des réseaux de neurones." Thesis, Artois, 2010. http://www.theses.fr/2010ARTO0407/document.
Full textThe artificial neural networks are successfully applied in many applications. But theusers are confronted with two problems : defining the architecture of the neural network able tosolve their problems and interpreting the network result. Many research works propose some solutionsabout these problems : to find out the architecture of the network, some authors proposeto use the problem domain theory and deduct the network architecture and some others proposeto dynamically add neurons in the existing networks until satisfaction. For the interpretabilityproblem, solutions consist to extract rules which describe the network behaviour after training.The contributions of this thesis concern these problems. The thesis are limited to the use of theartificial neural networks in solving the classification problem.In this thesis, we present a state of art of the existing methods of finding the neural networkarchitecture : we present a theoritical and experimental study of these methods. From this study,we observe some limits : difficulty to use some method when the knowledges are not available ;and the network is seem as ’black box’ when using other methods. We a new method calledCLANN (Concept Lattice-based Artificial Neural Network) which builds from the training dataa semi concepts lattice and translates this semi lattice into the network architecture. As CLANNis limited to the two classes problems, we propose MCLANN which extends CLANN to manyclasses problems.A new method of rules extraction called ’MaxSubsets Approach’ is also presented in thisthesis. Its particularity is the possibility of extracting the two kind of rules (If then and M-of-N)from an internal structure.We describe how to explain the MCLANN built network result aboutsome inputs
Voegtlin, Thomas. "Réseaux de neurones et auto-référence." Lyon 2, 2002. http://theses.univ-lyon2.fr/documents/lyon2/2002/voegtlin_t.
Full textThe purpose of this thesis is to present a class of unsupervised learning algorithms for recurrent networks. In the first part (chapters 1 to 4), I propose a new approach to this question, based on a simple principle: self-reference. A self-referent algorithm is not based on the minimization of an objective criterion, such as an error function, but on a subjective function, that depends on what the network has previously learned. An example of a supervised recurrent network where learning is self-referent is the Simple Recurrent Network (SRN) by Elman (1990). In the SRN, self-reference is applied to the supervised error back-propagation algorithm. In this aspect, the SRN differs from other generalizations of back-propagation to recurrent networks, that use an objective criterion, such as Back-Propagation Through Time, or Real-Time Recurrent Learning. In this thesis, I show that self-reference can be combined with several well-known unsupervised learning methods: the Self-Organizing Map (SOM), Principal Components Analysis (PCA), and Independent Components Analysis (ICA). These techniques are classically used to represent static data. Self-reference allows one to generalize these techniques to time series, and to define unsupervised learning algorithms for recurrent networks
Teytaud, Olivier. "Apprentissage, réseaux de neurones et applications." Lyon 2, 2001. http://theses.univ-lyon2.fr/documents/lyon2/2001/teytaud_o.
Full textBooks on the topic "Réseaux de neurones LSTM"
Michel, Verleysen, ed. Les réseaux de neurones artificiels. Paris: Presses universitaires de France, 1996.
Find full textKamp, Yves. Réseaux de neurones récursifs pour mémoires associatives. Lausanne: Presses polytechniques et universitaires romandes, 1990.
Find full textRollet, Guy. Les RÉSEAUX DE NEURONES DE LA CONSCIENCE - Approche multidisciplinaire du phénomène. Paris: Editions L'Harmattan, 2013.
Find full textPersonnaz, L. Réseaux de neurones formels pour la modélisation, la commande et la classification. Paris: CNRS Editions, 2003.
Find full textAmat, Jean-Louis. Techniques avancées pour le traitement de l'information: Réseaux de neurones, logique floue, algorithmes génétiques. 2nd ed. Toulouse: Cépaduès-Ed., 2002.
Find full textJournées d'électronique (1989 Lausanne, Switzerland). Réseaux de neurones artificiels: Comptes rendus des Journées d'électronique 1989, Lausanne, 10-12 october 1983. Lausanne: Presses polytechniques romande, 1989.
Find full textSeidou, Ousmane. Modélisation de la croissance de glace de lac par réseaux de neurones artificiels et estimation du volume de la glace abandonnée sur les berges des réservoirs hydroélectriques pendant les opérations d'hiver. Québec, QC: INRS--ETE, 2005.
Find full textSuzanne, Tyc-Dumont, ed. Le neurone computationnel: Histoire d'un siècle de recherches. Paris: CNRS, 2005.
Find full textBiophysics of computation: Information processing in single neurons. New York: Oxford University Press, 1999.
Find full textK, Kaczmarek Leonard, ed. The neuron: Cell and molecular biology. 3rd ed. Oxford: Oxford University Press, 2002.
Find full textBook chapters on the topic "Réseaux de neurones LSTM"
Martaj, Dr Nadia, and Dr Mohand Mokhtari. "Réseaux de neurones." In MATLAB R2009, SIMULINK et STATEFLOW pour Ingénieurs, Chercheurs et Etudiants, 807–78. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-11764-0_17.
Full textKipnis, C., and E. Saada. "Un lien entre réseaux de neurones et systèmes de particules: Un modele de rétinotopie." In Lecture Notes in Mathematics, 55–67. Berlin, Heidelberg: Springer Berlin Heidelberg, 1996. http://dx.doi.org/10.1007/bfb0094641.
Full text"4. Les réseaux de neurones artificiels." In L'intelligence artificielle, 91–112. EDP Sciences, 2021. http://dx.doi.org/10.1051/978-2-7598-2580-6.c006.
Full textMOLINIER, Matthieu, Jukka MIETTINEN, Dino IENCO, Shi QIU, and Zhe ZHU. "Analyse de séries chronologiques d’images satellitaires optiques pour des applications environnementales." In Détection de changements et analyse des séries temporelles d’images 2, 125–74. ISTE Group, 2024. http://dx.doi.org/10.51926/iste.9057.ch4.
Full textBYTYN, Andreas, René AHLSDORF, and Gerd ASCHEID. "Systèmes multiprocesseurs basés sur un ASIP pour l’efficacité des CNN." In Systèmes multiprocesseurs sur puce 1, 93–111. ISTE Group, 2023. http://dx.doi.org/10.51926/iste.9021.ch4.
Full textBENMAMMAR, Badr, and Asma AMRAOUI. "Application de l’intelligence artificielle dans les réseaux de radio cognitive." In Gestion et contrôle intelligents des réseaux, 233–60. ISTE Group, 2020. http://dx.doi.org/10.51926/iste.9008.ch9.
Full textCOGRANNE, Rémi, Marc CHAUMONT, and Patrick BAS. "Stéganalyse : détection d’information cachée dans des contenus multimédias." In Sécurité multimédia 1, 261–303. ISTE Group, 2021. http://dx.doi.org/10.51926/iste.9026.ch8.
Full textATTO, Abdourrahmane M., Héla HADHRI, Flavien VERNIER, and Emmanuel TROUVÉ. "Apprentissage multiclasse multi-étiquette de changements d’état à partir de séries chronologiques d’images." In Détection de changements et analyse des séries temporelles d’images 2, 247–71. ISTE Group, 2024. http://dx.doi.org/10.51926/iste.9057.ch6.
Full textDE’ FAVERI TRON, Alvise. "La détection d’intrusion au moyen des réseaux de neurones : un tutoriel." In Optimisation et apprentissage, 211–47. ISTE Group, 2023. http://dx.doi.org/10.51926/iste.9071.ch8.
Full textATTO, Abdourrahmane M., Fatima KARBOU, Sophie GIFFARD-ROISIN, and Lionel BOMBRUN. "Clustering fonctionnel de séries d’images par entropies relatives." In Détection de changements et analyse des séries temporelles d’images 1, 121–38. ISTE Group, 2022. http://dx.doi.org/10.51926/iste.9056.ch4.
Full textConference papers on the topic "Réseaux de neurones LSTM"
Fourcade, A. "Apprentissage profond : un troisième oeil pour les praticiens." In 66ème Congrès de la SFCO. Les Ulis, France: EDP Sciences, 2020. http://dx.doi.org/10.1051/sfco/20206601014.
Full textGresse, Adrien, Richard Dufour, Vincent Labatut, Mickael Rouvier, and Jean-François Bonastre. "Mesure de similarité fondée sur des réseaux de neurones siamois pour le doublage de voix." In XXXIIe Journées d’Études sur la Parole. ISCA: ISCA, 2018. http://dx.doi.org/10.21437/jep.2018-2.
Full textORLIANGES, Jean-Christophe, Younes El Moustakime, Aurelian Crunteanu STANESCU, Ricardo Carrizales Juarez, and Oihan Allegret. "Retour vers le perceptron - fabrication d’un neurone synthétique à base de composants électroniques analogiques simples." In Les journées de l'interdisciplinarité 2023. Limoges: Université de Limoges, 2024. http://dx.doi.org/10.25965/lji.761.
Full textWalid, Tazarki, Fareh Riadh, and Chichti Jameleddine. "La Prevision Des Crises Bancaires: Un essai de modélisation par la méthode des réseaux de neurones [Not available in English]." In International Conference on Information and Communication Technologies from Theory to Applications - ICTTA'08. IEEE, 2008. http://dx.doi.org/10.1109/ictta.2008.4529985.
Full textKim, Lila, and Cédric Gendrot. "Classification automatique de voyelles nasales pour une caractérisation de la qualité de voix des locuteurs par des réseaux de neurones convolutifs." In XXXIVe Journées d'Études sur la Parole -- JEP 2022. ISCA: ISCA, 2022. http://dx.doi.org/10.21437/jep.2022-82.
Full textGendrot, Cedric, Emmanuel Ferragne, and Anaïs Chanclu. "Analyse phonétique de la variation inter-locuteurs au moyen de réseaux de neurones convolutifs : voyelles seules et séquences courtes de parole." In XXXIVe Journées d'Études sur la Parole -- JEP 2022. ISCA: ISCA, 2022. http://dx.doi.org/10.21437/jep.2022-94.
Full textQuintas, Sebastião, Alberto Abad, Julie Mauclair, Virginie Woisard, and Julien Pinquier. "Utilisation de réseaux de neurones profonds avec attention pour la prédiction de l’intelligibilité de la parole de patients atteints de cancers ORL." In XXXIVe Journées d'Études sur la Parole -- JEP 2022. ISCA: ISCA, 2022. http://dx.doi.org/10.21437/jep.2022-7.
Full text