Дисертації з теми "Rete neurali"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Rete neurali".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
De, Paoli Davide. "Reti neurali artificiali e apprendimenti basati sulla biofisica dei neuroni." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/22983/.
Повний текст джерелаVincenzi, Fabian. "Reti neurali convoluzionali per il miglioramento di immagini tomografiche ad angoli limitati." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/22199/.
Повний текст джерелаSangiorgi, Davide. "Magnetic resonance fingerprinting con reti neurali a valori complessi." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18746/.
Повний текст джерелаFabbri, Alessandro. "Reti neurali in ambito finanziario." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19593/.
Повний текст джерелаFiori, Simona. "Memoria semantica e lessicale: analisi attraverso una rete neurale." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2012. http://amslaurea.unibo.it/4688/.
Повний текст джерелаPaganelli, Michele. "Studio dell'attenzione dei conducenti tramite i sistemi neurali." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Знайти повний текст джерелаDi, Stefano Tiziano. "Metodologie di training per reti neurali di tipo autoencoder." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017.
Знайти повний текст джерелаVece, Michele. "Rete neurale per la predizione del ritardo nel pagamento delle fatture." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19578/.
Повний текст джерелаDi, Tommaso Claudia. "Meccanismi neurali per la rappresentazione semantica e lessicale: modello di una rete neurale per apprendere il significato di oggetti e parole." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2014. http://amslaurea.unibo.it/7910/.
Повний текст джерелаFormentin, Sara Mizar. "Analisi della interazione onda - struttura mediante reti neurali. La riflessione ondosa." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2011. http://amslaurea.unibo.it/2859/.
Повний текст джерелаCiliegi, Federico. "Topologie non convenzionali per reti di neuroni artificiali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19497/.
Повний текст джерелаCotugno, Giosuè. "Dall’IA all’olio: come affinare i sistemi di classificazione della qualità attraverso tecniche di machine learning con l’utilizzo di reti neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20837/.
Повний текст джерелаTaddei, Annalisa. "Studio e ottimizzazione della rete neurale HTM per la rilevazione di emissioni acustiche." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/21483/.
Повний текст джерелаGentile, Gloria. "Analisi di Sensitività di una Rete neurale per l’interazione visuo-tattile bilaterale." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Знайти повний текст джерелаZucchi, Lorenzo. "Fenomeni visivi durante movimenti oculari saccadici: studio mediante modello di rete neurale." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17918/.
Повний текст джерелаOrlandini, Lucrezia. "Applicazione di reti neurali per l’implementazione di un modello di demand forecasting in ambito fashion." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Знайти повний текст джерелаAngeli, Teresa. "Applicazione delle reti neurali residuali ai mercati energetici e loro interpretazione come problema di controllo ottimo stocastico." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23925/.
Повний текст джерелаCodicè, Francesco. "Rete neurale per la predizione end-to-end dello stato di ossidazione delle cisteine e la connettività dei ponti disolfuro." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20593/.
Повний текст джерелаMonti, Alice. "Modelli neuro-computazionali di memoria semantica: analisi dell'apprendimento dipendente dal contesto e sincronismo neurale." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19025/.
Повний текст джерелаRainò, Luigi Armando. "Metodo speditivo per la valutazione del comportamento strutturale di edifici intelaiati in calcestruzzo armato: studio dell’influenza della forma e delle caratteristiche costruttive mediante l’applicazione di reti neurali." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017.
Знайти повний текст джерелаRusso, Giulio. "Metodi speditivi per la valutazione del comportamento strutturale di edifici intelaiati in c.a. mediante l'applicazione di reti neurali. Studio dell'influenza delle caratteristiche meccaniche e geometriche: analisi e valutazione dei risultati." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Знайти повний текст джерелаGnucci, Valentina. "Metodi speditivi per la valutazione del comportamento strutturale di edifici intelaiati in c.a. mediante l'applicazione di reti neurali. Studio dell'influenza delle caratteristiche meccaniche e geometriche: scelta dei parametri di analisi." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Знайти повний текст джерелаScalella, Martina. "Analisi del ventriloquismo temporale mediante rete neurale." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/11532/.
Повний текст джерелаSoncini, Filippo. "Classificazione di documenti tramite reti neurali." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20509/.
Повний текст джерелаDamiani, Lucia. "Studio dell'integrazione multisensoriale nella corteccia attraverso rete neurale." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/9741/.
Повний текст джерелаSousa, Fabiano Berardo de. "Análise de modelo de Hopfield com topologia de rede complexa." Universidade de São Paulo, 2013. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-30012014-111520/.
Повний текст джерелаBiological neural networks contain billions of neurons divided in spatial and functional clusters to perform dierent tasks. It also operates with complex dynamics such as periodic and chaotic ones. It has been shown that Chaotic Neural Networks are more efficient than conventional recurrent neural networks in avoiding spurious memory. Inspired by the fact that the cerebral cortex has speficic groups of cells and motivated by the efficiency of complex behaviors, in this document we investigate the dynamics of a recurrent neural network, as the Hopfield one, but with neurons coupled in such a way to form a complex network community structure. Also, we generate an asymmetric weight matrix placing pattern cycles during learning. Our study shows that the network can operate with periodic and chaotic dynamics, depending on the degree of the connection\'s fragmentation. For low fragmentation degree, the network operates with periodic dynamic duo to the employed learning rule. Chaotic behavior seems to rise for a high fragmentation degree. We also show that the neural network can hold both chaotic dynamic and a high value of modularity measure at the same time, indicating an acceptable community structure. These findings provide an alternative way to design dynamical neural networks to perform pattern recognition tasks exploiting periodic and chaotic dynamics by using a more similar topology to the topology of the brain
Corazza, Michele. "Coreference Resoultion basata su reti neurali deep." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/14554/.
Повний текст джерелаVagnoni, Ulderico. "Analisi di immagini storiche con reti neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19624/.
Повний текст джерелаBrigandì, Camilla. "Utilizzo della omologia persistente nelle reti neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Знайти повний текст джерелаZANCATO, LUCA. "Sull'addestrabilità e generalizzazione delle Reti Neurali Profonde." Doctoral thesis, Università degli studi di Padova, 2022. http://hdl.handle.net/11577/3446030.
Повний текст джерелаThe last few years have witnessed the rise of Deep Neural Networks. Since the introduction of AlexNet in 2012, the community of researchers and industries employing Deep Learning has exploded. This surge in attention led to the development of State of The Art algorithms in many different fields such as Computer Vision, Natural Language Processing and Time Series modeling. The empirical success of Deep Learning posed new methodological challenges for academia and allowed industry to deploy world-wide large scale web services unthinkable ten years ago. Despite such incontrovertible success, Deep Learning does not come free of issues: model design is highly costly, model interpretability is not easy, deployment often requires very specialized experts and, not least, any Deep Neural Network requires a large amount of data for training. Moreover, from a theoretical standpoint many important guarantees on optimization convergence and generalization are still lacking. In this thesis we address trainability and generalization of Deep Neural Network models: we analyze the optimization trajectories and the generalization of typical over-parametrized models; moreover, we design a specialized inductive bias and regularization scheme to foster interpretability and generalization of Deep Neural Networks. The starting point in our analysis is a recently proposed tool: the Neural Tangent Kernel for over-parametrized models. Building on this fundamental result, we investigate the number of optimization steps that a pre-trained Deep Neural Network needs to converge to a given value of the loss function ("Training Time"). Moreover, we exploit the Neural Tangent Kernel theory to solve the problem of choosing the best pre-trained Deep Neural Network within a "model zoo" when only the target dataset is known and without training any model ("Model Selection"). Our analysis started to unblock the adoption of real-world Computer Vision AutoML systems: Users fine-tune models selected from a large "model zoo" testing hundreds of combinations of different architectures, pre-training sets and hyper-parameters, but are reluctant to do so without an estimate of the expected training cost. Our results are a step towards better understanding of transfer learning through a novel study on the interplay between generalization and highly over-parametrized Deep Neural Networks. We then build a specialized Deep architecture equipped with a strong inductive bias and explicit regularization, that are designed both to constrain the representational power of our architecture and to allow Bayesian automatic complexity selection. Then, we show our novel method can be successfully applied both for non-linear System Identification and for Anomaly Detection of large scale Time Series.
Cino, G. "Implementazione ed analisi di reti neurali wetware." Doctoral thesis, Università degli Studi di Milano, 2007. http://hdl.handle.net/2434/180804.
Повний текст джерелаCiotti, Lorenzo. "Rete Neurale per il Raffinamento di Mappe di Disparità." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.
Знайти повний текст джерелаMenegaz, Mauricio. "Aplicação da rede GTSOM para navegação de robôs móveis utilizando aprendizado por reforço." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2009. http://hdl.handle.net/10183/22816.
Повний текст джерелаThis work describes an architecture for an autonomous robotic agent that is capable of creating a state representation of its environment and learning how to execute simple tasks using this representation. The GTSOM Neural Network was chosen as the method for state clustering. It is used to transform the multidimensional and continuous state signal into a discrete representation, allowing the use of conventional reinforcement learning techniques. Some modifications on the algorithm were necessary so that it could be used in this project. This network is used together with a grid map algorithm that allows the model to associate the sensor readings with the places where they ocurred. While the GTSOM network is the main component of a state clustering system, the Q-Learning reinforcement learning method was chosen for the task execution. Using the compact state representation created by the self-organizing network, the agent learns which actions to execute at each state in order to achieve its objectives. The model was tested in an experiment that consists in finding the path in a maze. The results show that it can divide the state space in an useful way, and is capable of executing the task. It learns to avoid collisions and remembers the location of the target, even when the robot’s initial position is changed. Furthermore, the representation is expanded when the agent faces an unknown situation, and at the same time, states associated with old experiences are forgotten.
Negrini, Melissa. "Tatto artificiale: studio ed implementazione di una rete neurale per la localizzazione di impatti." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/17342/.
Повний текст джерелаD'Amato, Ester. "Simulazione di attività neuroelettrica corticale durante compiti motori in pazienti post-ictus con lesione unilaterale." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17487/.
Повний текст джерелаDi, Luzio Andrea. "Reti Neurali Convoluzionali per il riconoscimento di caratteri." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016.
Знайти повний текст джерелаSerluca, Alberto. "Behavioural Cloning in Ambiente Simulato con Reti Neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/15711/.
Повний текст джерелаPolini, Elena. "Super Resolution di immagini con reti neurali convoluzionali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18502/.
Повний текст джерелаBallestrazzi, Francesco. "Reti neurali iterative per la generazione di immagini." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18503/.
Повний текст джерелаGiunchi, Massimiliano. "Reti neurali per la segmentazione di immagini mediche." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Знайти повний текст джерелаCielo, Michele. "Rilevamento di malattie oculari mediante reti neurali artificiali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19750/.
Повний текст джерелаTorchi, Andrea. "Sperimentazioni per "Sentiment Analysis" tramite Reti Neurali Profonde." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Знайти повний текст джерелаAccornero, Andrea. "Covid-19 x-ray Analisi con reti neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24952/.
Повний текст джерелаSuzzi, Mattia. "Introduzione al Machine Learning e alle reti neurali." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Знайти повний текст джерелаMollica, Francesco. "Share Art: Reti neurali convoluzionali in ambito museale." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Знайти повний текст джерелаSartorello, Michele <1990>. "Prezzi predatori e reti neurali: un approccio sperimentale." Master's Degree Thesis, Università Ca' Foscari Venezia, 2014. http://hdl.handle.net/10579/5210.
Повний текст джерелаBoldrin, Stefano <1996>. "Reti neurali artificiali per la previsione dell'insolvenza aziendale." Master's Degree Thesis, Università Ca' Foscari Venezia, 2020. http://hdl.handle.net/10579/18258.
Повний текст джерелаFurini, Marcos Amorielle [UNESP]. "Projeto de controladores suplementares de amortecimento utilizando redes neurais artificiais." Universidade Estadual Paulista (UNESP), 2011. http://hdl.handle.net/11449/100323.
Повний текст джерелаCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Neste trabalho é proposta a utilização da rede neural artificial (RNA) ARTMAP Nebulosa (fuzzy) no ajuste de parâmetros de controladores suplementares para o amortecimento de oscilações eletromecânicas de sistemas elétricos de potência, visando tornar este ajuste mais eficiente. Análises comparativas da atuação das redes neurais artificiais ARTMAP Nebulosa e Perceptron Multicamadas (PM) são realizadas para dois sistemas multimáquinas considerando o ajuste individual e coordenado dos controladores. Tais redes são utilizadas para o projeto dos controladores ESP (Estabilizadores de Sistemas de Potência) e POD (Power Oscillation Damping) acoplado ao dispositivo FACTS (Flexible Alternating Current Transmission Systems) UPFC (Unified Power Flow Controller). Será evidenciado que a RNA ARTMAP Nebulosa pode ser utilizada na melhora da estabilidade dinâmica, fornecendo resultados muito semelhantes aos da RNA Perceptron Multicamadas. Entretanto, é importante enfatizar que a vantagem da utilização da RNA ARTMAP Nebulosa está no fato da garantia da estabilidade e plasticidade associadas a um rápido treinamento, o que não ocorre com a RNA Perceptron Multicamadas
This work proposes the use of artificial neural network (ANN) Fuzzy ARTMAP to adjust the parameters of additional controllers to damp electromechanical oscillations in electric power systems in order to make this adjustment more efficient due to variations in load. Comparative analysis of the performance of artificial neural networks Fuzzy ARTMAP and Multilayer Perceptron are performed for two multimachine systems, considering individual and coordinated controller adjustment. Those networks are used for the design of Power System Stabilizers (PSS) and Power Oscillation Damping (POD) that is coupled to the FACTS (Flexible Alternating Current Transmission Systems) UPFC (Unified Power Flow Controller). It will be shown that the ANN Fuzzy ARTMAP can be used in the improvement of dynamic stability, providing very similar results to the ANN Multilayer Perceptron. However, it is important to emphasize that the advantage of using ANN Fuzzy ARTMAP is the guarantee of stability and plasticity associated with a fast training process which does not occur for the ANN Multilayer Perceptron
Maestri, Rita. "Metodiche di deep learning e applicazioni all’imaging medico: la radiomica." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/15452/.
Повний текст джерелаNaldi, Elisa. "Implementazione in FPGA di una rete neurale convolutiva profonda per l'elaborazione in tempo reale di immagini." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16456/.
Повний текст джерела