Tesi sul tema "Hardware pour l'intelligence artificielle"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-34 saggi (tesi di laurea o di dottorato) per l'attività di ricerca sul tema "Hardware pour l'intelligence artificielle".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi le tesi di molte aree scientifiche e compila una bibliografia corretta.
Janzakova, Kamila. "Développement de dendrites polymères organiques en 3D comme dispositif neuromorphique". Electronic Thesis or Diss., Université de Lille (2022-....), 2023. http://www.theses.fr/2023ULILN017.
Neuromorphic technologies is a promising direction for development of more advanced and energy-efficient computing. They aim to replicate attractive brain features such as high computational efficiency at low power consumption on a software and hardware level. At the moment, brain-inspired software implementations (such as ANN and SNN) have already shown their successful application for different types of tasks (image and speech recognition). However, to benefit more from the brain-like algorithms, one may combine them with appropriate hardware that would also rely on brain-like architecture and processes and thus complement them. Neuromorphic engineering has already shown the utilization of solid-state electronics (CMOS circuits, memristor) for the development of brain-inspired devices. Nevertheless, these implementations are fabricated through top-down methods. In contrast, brain computing relies on bottom-up processes such as interconnectivity between cells and the formation of neural communication pathways.In the light of mentioned above, this work reports on the development of programmable 3D organic neuromorphic devices, which, unlike most current neuromorphic technologies, can be created in a bottom-up manner. This allows bringing neuromorphic technologies closer to the level of brain programming, where necessary neural paths are established only on the need.First, we found out that PEDOT:PSS based 3D interconnections can be formed by means of AC-bipolar electropolymerization and that they are capable of mimicking the growth of neural cells. By tuning individually the parameters of the waveform (peak amplitude voltage -VP, frequency - f, duty cycle - dc and offset voltage - Voff), a wide range of dendrite-like structures was observed with various branching degrees, volumes, surface areas, asymmetry of formation, and even growth dynamics.Next, it was discovered that dendritic morphologies obtained at various frequencies are conductive. Moreover, each structure exhibits an individual conductance value that can be interpreted as synaptic weight. More importantly, the ability of dendrites to function as OECT was revealed. Different dendrites exhibited different performances as OECT. Further, the ability of PEDOT:PSS dendrites to change their conductivity in response to gate voltage was used to mimic brain memory functions (short-term plasticity -STP and long-term plasticity -LTP). STP responses varied depending on the dendritic structure. Moreover, emulation of LTP was demonstrated not only by means of an Ag/AgCl gate wire but as well by means of a self-developed polymer dendritic gate.Finally, structural plasticity was demonstrated through dendritic growth, where the weight of the final connection is governed according to Hebbian learning rules (spike-timing-dependent plasticity - STDP and spike-rate-dependent plasticity - SRDP). Using both approaches, a variety of dendritic topologies with programmable conductance states (i.e., synaptic weight) and various dynamics of growth have been observed. Eventually, using the same dendritic structural plasticity, more complex brain features such as associative learning and classification tasks were emulated.Additionally, future perspectives of such technologies based on self-propagating polymer dendritic objects were discussed
Voyiatzis, Konstantinos. "Utilisation de l'intelligence artificielle pour les problèmes d'ordonnancement". Paris 9, 1987. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1987PA090102.
The present work concerns the scheduling of the products in a production system from "jobshop" type. This problem is a combinatorial problem and has an incompatible solution with the "real time" contraint. We demonstrate in which way this approach "artificial intelligence" can conduct to an acceptable scheduling in real time. The first chapter presents the structure of the artificial memory we use. The second one tells us an example of utilization on this approach. The appendix i remains the basis of production managment. The appendix ii gives us the basis of the automatic classification used in severals parts of this work. And the appendix iii, contains the software of simulation written in slam
Voyiatzis, Konstantinos. "Utilisation de l'intelligence artificielle pour les problèmes d'ordonnancement". Grenoble 2 : ANRT, 1987. http://catalogue.bnf.fr/ark:/12148/cb376106812.
Neggaz, Mohamed Ayoub. "Accélérateurs Matériels pour l'Intelligence Artificielle. Etude de Cas : Voitures Autonomes". Thesis, Valenciennes, Université Polytechnique Hauts-de-France, 2020. http://www.theses.fr/2020UPHF0017.
Since the early days of the DARPA challenge, the design of self-driving cars is catching increasing interest. This interest is growing even more with the recent successes of Machine Learning algorithms in perception tasks. While the accuracy of thesealgorithms is irreplaceable, it is very challenging to harness their potential. Realtime constraints as well as reliability issues heighten the burden of designing efficient platforms.We discuss the different implementations and optimization techniques in this work. We tackle the problem of these accelerators from two perspectives: performance and reliability. We propose two acceleration techniques that optimize time and resource usage. On reliability, we study the resilience of Machine Learning algorithms. We propose a tool that gives insights whether these algorithms are reliable enough forsafety critical systems or not. The Resistive Associative Processor accelerator achieves high performance due to its in-memory design which remedies the memory bottleneck present in most Machine Learning algorithms. As for the constant multiplication approach, we opened the door for a new category of optimizations by designing instance specific accelerators. The obtained results outperforms the most recent techniques in terms of execution time and resource usage. Combined with the reliability study we conducted, safety-critical systems can profit from these accelerators without compromising its security
Gaïti, Dominique. "L'utilisation des techniques de l'intelligence artificielle pour la gestion des reseaux". Paris 6, 1991. http://www.theses.fr/1991PA066493.
Claes, Gérard. "Contribution à l'application de l'intelligence artificielle pour l'enseignement assisté par ordinateur". Paris 11, 1988. http://www.theses.fr/1988PA112412.
Claes, Gérard. "Contribution à l'application de l'intelligence artificielle pour l'enseignement assisté par ordinateur". Grenoble 2 : ANRT, 1988. http://catalogue.bnf.fr/ark:/12148/cb376127000.
Levasseur, Yan. "Techniques de l'intelligence artificielle pour la classification d'objets biologiques dans des images bidimensionnelles". Mémoire, École de technologie supérieure, 2008. http://espace.etsmtl.ca/115/1/LEVASSEUR_Yan.pdf.
CHERIE, NABIL. "Utilisation des techniques de l'intelligence artificielle pour la modelisation du mouvement d'objets animes". Paris 11, 1991. http://www.theses.fr/1991PA112075.
Panaïotis, Thelma. "Distribution du plancton à diverses échelles : apport de l'intelligence artificielle pour l'écologie planctonique". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS155.
As the basis of oceanic food webs and a key component of the biological carbon pump, planktonic organisms play major roles in the oceans. However, their small-scale distribution − governed by biotic interactions between organisms and interactions with the physico-chemical properties of the water masses in their immediate environment − are poorly described in situ due to the lack of suitable observation tools. New instruments performing high resolution imaging in situ in combination with machine learning algorithms to process the large amount of collected data now allows us to address these scales. The first part of this work focuses on the methodological development of two automated pipelines based on artificial intelligence. These pipelines allowed to efficiently detect planktonic organisms within raw images, and classify them into taxonomical or morphological categories. Then, in a second part, numerical ecology tools have been applied to study plankton distribution at different scales, using three different in situ imaging datasets. First, we investigated the link between plankton community and environmental conditions at the global scale. Then, we resolved plankton and particle distribution across a mesoscale front, and highlighted contrasted periods during the spring bloom. Finally, leveraging high frequency in situ imaging data, we investigated the fine-scale distribution and preferential position of Rhizaria, a group of understudied, fragile protists, some of which are mixotrophic. Overall, these studies demonstrate the effectiveness of in situ imaging combined with artificial intelligence to understand biophysical interactions in plankton and distribution patterns at small-scale
Zarri, Gian Piero. "Utilisation de techniques relevant de l'intelligence artificielle pour le traitement de données biographiques complexes". Paris 11, 1985. http://www.theses.fr/1985PA112342.
The aim of this thesis is to provide a general description of RESEDA, an « intelligent » Information Retrieval system dealing with biographical data and using techniques borrowed from Knowledge Engineering and Artificial Intelligence (AI). All the system’s “knowledge” is represented in purely declarative form. This is the case both for the “fact database” and the “rule base”; the fact database contains the data, in the usual sens of the word that the system has to retrieve. Together, the fact and rule bases make up RESEDA’s “knowledge base”. Information in the knowledge base is depicted using a single knowledge representation language (“metalanguage”), which makes use of quantified variables when describing date in the rule base; the metalanguage is a particularly powerful realization of an AI type “case grammar”. For reasons of computational efficiency, the low-level (“level zero”) inferencing (retrieving) is carried out in RESEDA by using only the resources of the system’s match machine. This machine owes a large part of its power to the judicious use of temporal data in efficiently indexing the fact database. Only high-level inferences require the creation of real “inference engines”. RESEDA’s inference engine hat the general characteristics a) of being “event driven” in its initialization; b) of solving problems by constructing a “choice tree”. Traversal of the choice tree is performed depth-first with systematic backtracking. The high-level inference operations, relying on information in the rule base and making use of the inference engine, that are implemented in the system, are known as “transformations” and “hypotheses”. The “hypotheses” enable new causal relationships to be established between events in the fact database which are a priori totally disjointed; the system is thus equipped with an, albeit elementary, learning capability
Panzoli, David. "Proposition de l'architecture "Cortexionist" pour l'intelligence comportementale de créatures artificielles". Toulouse 3, 2008. http://thesesups.ups-tlse.fr/458/.
Traditionally, producing intelligent behaviors for artificial creatures means modeling their cognitive abilities. This approach raises two problems. On the one hand, defining manually the agent's knowledge is a heavy duty that implies the intervention of the animator. On the other hand, the cognition-->intelligence relation has not been theoretically nor experimentally proven so far. In front of these challenges, ecological approaches appear as suitable tracks, exploring the links between the creature, its body and its environment. This is the context of the present research work. Using an artificial life approach, we propose an original model of memory based on the synthesis of several neuroscience theories. The Cortexionist controller is a reactive architecture integrating an associative network to enhance the agent's adaptation in a dynamic environment. Obtaining emerging behavior rules reveals the relation between the complexity of the environment and of the creatures that live in
Carle, Patrice. "Mering iv : un langage d'acteurs pour l'intelligence artificielle distribuee integrant objets et agents par reflexivite compilatoire". Paris 6, 1992. http://www.theses.fr/1992PA066429.
Perrin, Éric. "Stratégie intégrée utilisant des outils de l'intelligence artificielle pour la maîtrise d'un bioprocédé : instrumentation, modélisation, commande". Vandoeuvre-les-Nancy, INPL, 1996. http://www.theses.fr/1996INPL112N.
Motawej, Fadi. "Approche par invariance positive et les techniques de l'intelligence artificielle pour la régulation des carrefours signalisés". Phd thesis, Université de Technologie de Belfort-Montbeliard, 2012. http://tel.archives-ouvertes.fr/tel-00720655.
Elferkh, Jrad Zeina. "Apport des techniques de l'intelligence artificielle dans la négociation dynamique de niveaux de service : proposition d'une interface utilisateur pour l'Internet de nouvelle génération". Paris 13, 2006. http://www.theses.fr/2006PA132005.
Ndiaye, Soulemane. "Une approche multi-agents pour l'aide aux processus decisionnels complexes : une application a l'intelligence economique". Toulouse 1, 1997. http://www.theses.fr/1997TOU10079.
This thesis deals with complex decision making. First, different approaches dealing with decision making are investigated. Based upon that, a cognitive approach of decision is introduced and a model of complex decision making is proposed. This model is related to cognitive planning mechanisms (schema, anticipation), and construction and manipulation of models (operative models). In a second time, decision support and decision support systems are analysed. Systems and techniques related to complex decisions support are discussed. Complex decision support, in the perspective of augmenting managers' capacity, underlines the construction and manipulation of operative models. An agent oriented meta-model is proposed to support both activities. Lastly, simeco, a toolkit fully integrating this meta-model is presented. Simeco allows to create and modify applications implementing operative models. An application dedicated to economic intelligence is then described
Chiali, Abdelkrim. "Contribution de l'intelligence artificielle pour l'aide à la décision en formulation chimique : conception et exploitation de systèmes experts". Châtenay-Malabry, Ecole centrale de Paris, 1997. http://www.theses.fr/1997ECAP0533.
Alsabbah, Shebel Asad. "Mise en oeuvre de techniques issues de l'intelligence artificielle pour le contrôle de moteurs ultrasoniques à onde progressive". Paris 11, 2005. http://www.theses.fr/2005PA112190.
This thesis consists of two main parts: Firstly, a simplified analytical model, which represents the travelling wave ultrasonic motor, has been derived and evaluated, numerically and experimentally. With this model many control strategies can be investigated including conventional and fuzzy model-based control approaches. That is why, the second part of this thesis is designed to consider a comparative study of a rule-based fuzzy PID controller and a self-tuning controller STC for the ultrasonic piezoelectric motor drive system. The driving frequency which has an inversely non-linear relationship with the motor speed is used as a control variable. Different numerical and practical control solutions have been proposed and studied
Sghaier, Manel. "Combinaison des techniques d'optimisation et de l'intelligence artificielle distribuée pour la mise en place d'un système de covoiturage dynamique". Phd thesis, Ecole Centrale de Lille, 2011. http://tel.archives-ouvertes.fr/tel-00689957.
Kanta, Abdoul-Fatah. "Développement d'un système expert basé sur l'intelligence artificielle pour la prédiction et le contrôle du procédé de projection plasma". Besançon, 2007. http://www.theses.fr/2007BESA2013.
Atmospheric plasma spraying (APS) is a process in which the coating properties are indirectly linked to the selection of the operating parameters (power, injection kinematic and environmental parameters). This process is characterized by several parametric drifts and fluctuations at different characteristic times. These drifts and fluctuations originate especially from the electrode wear and intrinsic plasma jet instabilities. The objective of this work is to develop an expert system which could adjust in real time the operating parameters as a function, in a first time, of the measured in-flight particles to manufacture a coating. Due to the large amplitudes of these drifts an fluctuations, the strategy to adopt will depend on the required corrections to apply to the particle characteristics. Artificial intelligence base on artificial neural networks and fuzzy logic controller appeared as pertinent tools to reach this objective. Fuzzy logic permits to define parametric correction rules and the artificial neural networks permits to predict in-flight particle and coating characteristics. Coupling neural protocols to fuzze logic permit to develop an independent controller. This system offers the possibility to adjust the process parameters in order to improve the reproducibility of the process and also, to optimize the coatings development conditions by taking into account the effects of the electrode wear. The system is flexible in order to to permit a full control based on pre-defined rules aiming and maintaining at constant value the in-flight particle characteristics (surface temperature and velocity) by adjusting in real time pwer parameters whatever the fluctuations
Baujard, Olivier. "Conception d'un environnement de développement pour la résolution de problèmes : apport de l'intelligence artificielle distribuée et application à la vision". Phd thesis, Grenoble 1, 1992. http://tel.archives-ouvertes.fr/tel-00341607.
Synnaeve, Gabriel. "Programmation et apprentissage bayésien pour les jeux vidéo multi-joueurs, application à l'intelligence artificielle de jeux de stratégies temps-réel". Phd thesis, Université de Grenoble, 2012. http://tel.archives-ouvertes.fr/tel-00780635.
Baujard, Olivier Garbay Catherine. "Conception d'un environnement de développement pour la résolution de problèmes apport de l'intelligence artificielle distribuée et application à la vision /". S.l. : Université Grenoble 1, 2008. http://tel.archives-ouvertes.fr/tel-00341607.
Navarro, Laurent. "Niveau de détail dynamique et progressif de l'intelligence artificielle pour le passage à l'échelle dans la simulation de comportements humains à base d'agents". Paris 6, 2013. http://www.theses.fr/2013PA066422.
Les approches d’agrégation dynamique et mésoscopique ont donné naissance à une méthodologie unifiée et puissante pour la simulation d’un grand nombre d’agents, avec des comportements complexes au sein d’un environnement de grande taille. Sa structure peut être adaptée à un large spectre de modèles agent, pour un coût de conception modéré, principalement employé en expertise et en configuration. L’étude de son impact sur la cohérence de la simulation permet d’exhiber un petit ensemble de paramètres contrôlant la globalité du processus, et offrant potentiellement le compromis souhaité entre gain en ressources computationnelles et maintien de la cohérence de la simulation. Tout ceci met en évidence l’unicité et l’adaptabilité de cette méthodologie, qui peut être facilement reproduite grâce à son formalisme simple. Les résultats expérimentaux des approches d’agrégation dynamique et mésoscopique sont extrêmement encourageants, et ont permis à un simulateur de comportement humain à l’état de l’art de multiplier le nombre d’acteurs virtuels simulés pour une faible perte en cohérence de simulation. De plus, elles ont fourni des capacités d’analyse multi-niveaux tout en demeurant relativement imperceptibles aux utilisateurs. Leur intégration validée au sein d’un simulateur de comportement humain industriel est l’une des réalisations majeures de cette thèse. Enfin, ces approches n’en sont qu’à leurs balbutiements. Elles permettent d’ouvrir la voie à d’autres plus complexes, qui pourraient inclure des méthodes d’apprentissage automatique, facilitant la recherche des fonctions de mappage les plus appropriées entre représentations à différents niveaux de résolution, et la gestion native des interactions inter-résolutions. Le spectre applicatif extrêmement large, qui s’étend au-delà de la simulation de comportement humain, facilite l’exploration de ces sujets de recherche
ROKO, LEOPOLD. "Une approche genie logiciel pour optimiser les méthodes de planification et de résolution de problèmes dans le domaine de l'Intelligence Artificielle". Paris 7, 1992. http://www.theses.fr/1992PA077272.
Semertzidis, Michel T. "Developpement de methodes basees sur les mathematiques, l'informatique et l'intelligence artificielle pour l'alignement de sequences et la prediction de structures proteiques". Paris 7, 1994. http://www.theses.fr/1994PA077189.
Pujo, Pascal. "Développement d'une interface conviviale pour l'interrogation en langage naturel d'une base de données avec utilisation des concepts et des moyens de l'intelligence artificielle". Paris 11, 1989. http://www.theses.fr/1989PA112255.
Péloquin, Stéphane. "Utilisation de la télédétection, des SIG et de l'intelligence artificielle pour déterminer le niveau de susceptibilité aux mouvements de terrain : application dans les Andes de la Bolivie". Sherbrooke : Université de Sherbrooke, 1999.
Campos, Mario Cesar Mello Massa de. "La simulation dynamique et l'intelligence artificielle pour l'élaboration de stratégies de contrôle-commande multivariable flou : application à une unité de craquage catalytique en phase fluide". Châtenay-Malabry, Ecole centrale de Paris, 1997. http://www.theses.fr/1997ECAP0544.
Péloquin, Stéphane. "Utilisation de la télédétection, des SIG et de l'intelligence artificielle pour déterminer le niveau de susceptibilité aux mouvements de terrain application dans les Andes de la Bolivie". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape9/PQDD_0029/NQ61859.pdf.
Singer, Benjamin. "L'intelligence artificielle au service du rugby : acquisition et modélisationd'une expertise visuelle de prise de décision tactique : construction d'un système expert hybride d'aide à l'intervention pour la formation des joueurs et des cadres techniques". Paris 10, 1995. http://www.theses.fr/1995PA100048.
We focus on our contribution at the visual knowledge acquisition and modelling levels. After justifying its necessity we propose a visual knowledge elicitation language whose formal definition is given via its static and dynamic component s. The second part of our contribution is related to the design and realization of a visual knowledge acquisition software tool driven by the previous language. The third part of our contribution deals with visual knowledge modelling at the methodological and tool levels by extending the initial method and software. The fourth part describes the whole case study carried out for modelling the visual expertise considered for tactical decision-making in rugby the complete conceptual model is built. Then we describe the design, implementation and validation of the final expert system on the target architecture. The conclusion points out the interests of our contribution both at the theoretical and practical levels, and the generality of the results achieved for team games study
Chuquimia, Orlando. "Smart Vision Chip pour l’exploration du côlon". Electronic Thesis or Diss., Sorbonne université, 2019. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2019SORUS192.pdf.
CCR is the second highest cause of death by cancer worldwide with 880,792 deaths in 2018 and a mortality rate of 47.6%. 95% of CCR cases begin with the presence of a growth on the inner lining of the colon or the rectum, called a polyp. The endoscopic capsule was invented by Paul Swain in 1990. It is a pill incorpo- rating a camera and a radio communication system that the patient swallows and transmit images from the gastrointestinal tract through the body in a workstation. Once all images are transmitted, a gastroenterologist downloads them to perform a visual analysis and detect abnormalities and tumors. Using this device doctors can detect polyps, at least 5 mm, with sensitivity and specificity respectively of 68.8% and 81.3%. This endoscopic capsule presents some limitations and weaknesses re- lated to the spatial and temporal resolution of images, its energy autonomy and the number of images transmitted to be analyzed by the gastroenterologist. We studied the design of an embedded system containing a processing chain capable of detecting polyps to be integrated into an endoscopic capsule, creating a new medical device: an intelligent endoscopic capsule. To realize this device, we took into account all the non-functional constraints related to the integration into an endoscopic capsule. This device must be a new tool for early detection of precancerous colorectal lesions : polyps
Gandibleux, Xavier. "Système d'aide à la décision pour la conduite de processus perturbés ; une approche hybride fondée sur l'intelligence artificielle, la programmation linéaire et l'aide multicritère à la décision : application à la mobilisation de réserve tertiaire d'électricité de France". Valenciennes, 1995. https://ged.uphf.fr/nuxeo/site/esupversions/0a927862-e635-4e55-8aa3-955a2086752f.