Thèses sur le sujet « Algoritmi di apprendimento automatico »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 33 meilleures thèses pour votre recherche sur le sujet « Algoritmi di apprendimento automatico ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
Tullo, Alessandra. « Apprendimento automatico con metodo kernel ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23200/.
Texte intégralGiavoli, Andrea. « Analisi e applicazione dei processi di data mining al flusso informativo di sistemi real-time : Adattamento di un algoritmo di apprendimento automatico per la caratterizzazione e la ricerca di frequent patterns su macchine automatiche ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2015. http://amslaurea.unibo.it/9055/.
Texte intégralStefenelli, Marco. « Apprendimento automatico nei giochi di strategia ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2014. http://amslaurea.unibo.it/7660/.
Texte intégralUgolini, Matilde. « Metodologie di apprendimento automatico applicate alla generazione di dati 3D ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/10415/.
Texte intégralSPALLANZANI, MATTEO. « Un framework per l’analisi dei sistemi di apprendimento automatico ». Doctoral thesis, Università degli studi di Modena e Reggio Emilia, 2020. http://hdl.handle.net/11380/1200571.
Texte intégralMaking predictions is about getting insights into the patterns of our environment. We can access the physical world through media, measuring instruments, which provide us with data in which we hope to find useful patterns. The development of computing machines has allowed storing large data sets and processing them at high speed. Machine learning studies systems which can automate the detection of patterns in large data sets using computers. Machine learning lies at the core of data science and artificial intelligence, two research fields which are changing the economy and the society in which we live. Machine learning systems are usually trained and deployed on powerful computer clusters composed by hundreds or thousands of machines. Nowadays, the miniaturisation of computing devices is allowing deploying them on battery-powered systems embedded into diverse environments. With respect to computer clusters, these devices are far less powerful, but have the advantage of being nearer to the source of the data. On one side, this increases the number of applications of machine learning systems; on the other side, the physical limitations of the computing machines require identifying proper metrics to assess the fitness of different machine learning systems in a given context. In particular, these systems should be evaluated according not only to their modelling and statistical properties, but also to their algorithmic costs and their fitness to different computer architectures. In this thesis, we analyse modelling, algorithmic and architectural properties of different machine learning systems. We present the fingerprint method, a system which was developed to solve a business intelligence problem where statistical accuracy was more important than latency or energy constraints. Then, we analyse artificial neural networks and discuss their appealing computational properties; we also describe an example application, a model we designed to identify the objective causes of subjective driving perceptions. Finally, we describe and analyse quantized neural networks, artificial neural networks which use finite sets for the parameters and step activation functions. These limitations pose challenging mathematical problems, but quantized neural networks can be executed extremely efficiently on dedicated hardware accelerators, making them ideal candidates to deploy machine learning on edge computers. In particular, we show that quantized neural networks are equivalent to classical artificial neural networks (at least on the set of targets represented by continuous functions defined on compact domains); we also present a novel gradient-based learning algorithm for, named additive noise annealing, based on the regularisation effect of additive noise on the argument of discontinuous functions, reporting state-of-the-art results on image classification benchmarks.
TOMEI, MATTEO. « Riconoscimento di azioni nei video tramite tecnologie computazionali, multimediali e di apprendimento automatico ». Doctoral thesis, Università degli studi di Modena e Reggio Emilia, 2022. http://hdl.handle.net/11380/1271188.
Texte intégralVideo clips represent the most pervasive means of disseminating information nowadays. With their outbreak, needs for automatic categorization and content understanding have also increased, both for entertainment purposes and professional ones. In the context of multimedia and deep learning technologies for video comprehension, we explore and devise video-based algorithms and state-of-the-art solutions to tackle action recognition and fine-grained action localization. Our research is not limited to the quantitative evaluation of the proposed approaches for improving performance on specific tasks. We observe that handling video content usually brings some drawbacks. Videos often involve human actors and could arise privacy issues that are not yet sufficiently investigated by the computer vision community. Moreover, given their complexity and variability, videos are not easy to process and often require large computational resources. In addition to the application scenario, this thesis tackles two main challenges related to automatic video processing, namely privacy issues and computation. In the application part, we investigate the simultaneous detection of multiple actors and the classification of their actions, by exploiting interactions between people and surrounding objects, both in space and time. We also explore a more production-oriented application, in collaboration with Metaliquid SRL and in line with the company’s needs, by devising a deep network for salient action spotting in broadcast soccer matches. Regarding the privacy issue, we propose a novel strategy for masking people’s identities in video clips while preserving the ability of action recognition models to predict correct class labels. Finally, from the computational perspective, we develop an algorithm for reducing the size and resource utilization of existing deep neural networks, while keeping performances. These three aspects of video modeling are investigated separately but have proved to be generalizable, making it easier to build efficient and privacy-preserving action recognition models. All the alternatives and solutions presented in this work build upon deep learning, requiring a huge amount of data for learning video representations.
Bartolini, Manuel. « Sviluppo di algoritmi per l'automazione di misure industriali ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2012. http://amslaurea.unibo.it/3282/.
Texte intégralNigri, Simone. « Ottimizzatore per configurazione automatica di algoritmi di pattern matching ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Trouver le texte intégralLETTERI, IVAN. « Strategie di Miglioramento delle Prestazioni per rilevamento del traffico di malware con Modelli di Apprendimento Automatico ». Doctoral thesis, Università degli Studi dell'Aquila, 2020. http://hdl.handle.net/11697/163416.
Texte intégralTeci, Marco. « Implementazione e verifica degli algoritmi per il controllo di esposizione automatico nelle radiografie ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2013. http://amslaurea.unibo.it/6403/.
Texte intégralCozzetti, Rachele Agnese. « Valutazione dell'apprendimento di un nuovo dispositivo medico : l'iniettore automatico di CO2 Angiodroid ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Trouver le texte intégralHAMMAD, AHMED TAREK. « Tecniche di valutazione degli effetti dei Programmi e delle Politiche Pubbliche. L' approccio di apprendimento automatico causale ». Doctoral thesis, Università Cattolica del Sacro Cuore, 2022. http://hdl.handle.net/10280/110705.
Texte intégralThe analysis of causal mechanisms has been considered in various disciplines such as sociology, epidemiology, political science, psychology and economics. These approaches allow uncovering causal relations and mechanisms by studying the role of a treatment variable (such as a policy or a program) on a set of outcomes of interest or different intermediates variables on the causal path between the treatment and the outcome variables. This thesis first focuses on reviewing and exploring alternative strategies to investigate causal effects and multiple mediation effects using Machine Learning algorithms which have been shown to be particularly suited for assessing research questions in complex settings with non-linear relations. Second, the thesis provides two empirical examples where two Machine Learning algorithms, namely the Generalized Random Forest and Multiple Additive Regression Trees, are used to account for important control variables in causal inference in a data-driven way. By bridging a fundamental gap between causality and advanced data modelling, this work combines state of the art theories and modelling techniques.
Speciale, Giovanni Maria. « Il Ragionamento Logico come Forma di Apprendimento : Sviluppo di Un Framework per ILP ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23786/.
Texte intégralCappella, Matteo. « Studio e valutazione di tecniche di training per il riconoscimento automatico di attività attraverso dispositivi mobili ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017.
Trouver le texte intégralAlessandrini, Elena. « Analisi e riconoscimento automatico di impronte digitali latenti ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18429/.
Texte intégralAzolini, Flavio. « Modelli di deep learning e principali applicazioni ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2018.
Trouver le texte intégralBenincasa, Antonio. « Deep-learning per stima della confidenza di mappe depth ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.
Trouver le texte intégralBarbieri, Niccoló. « Trattamento del concetto di clustering a partire dalla definizione di misure di similarità e criteri valutativi ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24266/.
Texte intégralFariselli, Alberto. « Studio e implementazione di un sistema per la profilazione basato sul contesto e sul comportamento dell'utente ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2014. http://amslaurea.unibo.it/6637/.
Texte intégralDi, Gennaro Pierluigi. « Due approcci alla sentiment polarity classification di tweet per la lingua italiana ». Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/13270/.
Texte intégralLanera, Corrado. « Sviluppo e applicazione di tecniche di apprendimento automatico per l'analisi e la classificazione del testo in ambito clinico. Development and Application of Machine Learning Techniques for Text Analyses and Classification in Clinical Research ». Doctoral thesis, Università degli studi di Padova, 2020. http://hdl.handle.net/11577/3426256.
Texte intégralIl contenuto delle cartelle cliniche elettroniche (EHR) è estremamente eterogeneo, dipendendo della struttura generale del sistema sanitario. Al loro interno, il testo libero èprobabilmente la tipologia di dati non strutturato più presente e contemporaneamente sottoutilizzato. Al giorno d'oggi, grazie alle tecniche di Machine Learning (MLT), possiamo sfruttare modelli automatici per codificarne il contenuto testuale con prestazioni comparabili a quelle umane. In questa tesi, l'attenzione si concentra sull'investigazione delle MLT per l'ottenimento di informazioni utili non triviali dal testo libero in contesti clinici. Abbiamo considerato due tipi principali di testo libero coinvolti nella ricerca clinica. Il primo è composto da documenti estesi come articoli scientifici o protocolli di studio. Per questo gruppo, abbiamo preso in considerazione 14 revisioni sistematiche (SR), tra cui 7.494 studi di PubMed e un'intera istantanea composta da 233.609 studi clinici da ClinicalTrials.gov. Le cartelle cliniche elettroniche pediatriche compongono il secondo gruppo, per il quale abbiamo considerato due fonti di dati: una di 6.903.035 visite dal database italiano Pedianet e la seconda da 2.723 note di dimissione ospedaliera scritte in spagnolo e provenienti dai dipartimenti di emergenza (DE) pediatrica di nove ospedali in Nicaragua. Il primo contributo riportato è un sistema automatico addestrato per replicare una ricerca dai motori di ricerca specializzati ai registri clinici. Il modello proposto ha mostrato prestazioni di classificazione molto elevate (AUC dal 93,4% al 99,9% tra i 14 SR), con il valore aggiunto di una quantità ridotta di studi non rilevanti estratti (media di 472 e massimo di 2119 record aggiuntivi rispetto a 572 e 2680 dell'estrazione manuale originale rispettivamente). Viene riportato anche uno studio comparativo per esplorare l'effetto dell'utilizzo di differenti MLT e di metodi diversi per gestire gli effetti dello squilibro di numerosità nelle classi. Nella tesi è riportata inoltre un'intera indagine sulle visite pediatriche presso i DE raccolte presso i nove ospedali del Nicaragua. In tale indagine emerge un'accuratezza media nella classificazione delle diagnosi di dimissione coi modelli proposti del 78,31%, mostrando promettenti prestazioni per un sistema ML per la classificazione automatica delle diagnosi di dimissione da testo libero in lingua spagnola. Un ulteriore contributo riportato ha mirato a migliorare l'accuratezza del rilevamento delle malattie infettive a livello di popolazione. Questo è un problema cruciale per la salute pubblica che può fornire le informazioni di base necessarie per l'implementazione di strategie di controllo efficaci, come la notifica e il monitoraggio di efficacia di campagne di vaccinazione. Tra i due studi riportati, sono stati esplorati entrambi i paradigmi primari di ML classici e profondi. In entrambi i casi i risultati sono stati molto promettenti; nel secondo, raggiungendo prestazioni paragonabili a quelle umane (precisione del 96,59% rispetto al 95,91% raggiunta dagli annotatori umani e livello F1 bilanciato del 95,47% rispetto al 93,47%). Un ulteriore obiettivo secondario ma rilevante raggiunto riguarda le lingue indagate. La ricerca internazionale sull'uso delle MLT per classificare gli EHR si concentra principalmente su set di dati testuali in lingua inglese. Pertanto, i risultati su database non inglesi, come il Pedianet italiano o quello spagnolo delle visite ED considerate nella tesi, risultano contributi chiave per valutare l'applicabilità generale delle MLT a livello linguistico generale. Mostrando prestazioni paragonabili a quelle umane, la tesi evidenzia la reale possibilità di iniziare a incorporare i sistemi ML nella pratica clinica quotidiana per produrre un miglioramento concreto nei processi sanitari quando si tiene conto del testo libero.
GENEROSI, ANDREA. « Tecniche di Deep Learning per analizzare e migliorare la Customer Experience in contesti digitali e fisici ». Doctoral thesis, Università Politecnica delle Marche, 2020. http://hdl.handle.net/11566/274561.
Texte intégralThe digital transformation that today affects most industrial sectors has had a significant impact on the entire retail ecosystem, from the production to the sale and after-sale of products and services. This thesis work addresses this change by proposing a retail management methodology based on the concept of Customer Experience and innovative tools based on artificial intelligence systems, which together and integrated are able to enhance and make this transformation more effective. An important factor in the progressive changes in Retail concerns the introduction of technologies based on artificial intelligence, capable of collecting and interpreting a large amount of data generated by the various sales and customer contact channels, in order to improve the knowledge of the consumers, who are increasingly at the centre of the entire ecosystem, predict their behaviour, attitudes and preferences and activate personalised experiences capable of connecting them with the brand, with the result of increasing loyalty, sales and conversion rates. The customer's experience of a product, service or simply the environment in which they know the brand has become increasingly crucial in every process of design, production, sales, distribution and service that affects the retail ecosystem. The study on how to design and manage through new technologies the Customer Experience through precise actions in the different points of contact between customer and brand (touchpoints) is today the key for many retailers to achieve success in a market full of competitive challenges. In all touchpoints the customer interacts with the brand through the primary senses and there are different ways in which it reacts to the received stimuli, both rationally and emotionally: it is especially in this last case that the success in having a good CX is fundamental to ensure brand loyalty. Given the complexity of being able to monitor all the touchpoints, the design of a correct CX is often neglected if not completely omitted. Today, some of the most widely used methodologies to analyze the acceptance level of any experience by a user/customer, are very cumbersome and costly in terms of time and spent resources. In this context, the research on which this PhD thesis is focused is born, that is to find a technology able to automate data collection, interpret them to know the customer's response to a series of multisensory and multimedia stimuli and implement an adaptive CX that enables an empathic connection and involvement with the brand. To achieve this goal, this research will make use of pervasive and not intrusive tools and technologies, in order to obtain a large amount of data (Big Data) in the most "authentic" possible way, so to not contaminate the results by introducing unwanted bias: today these tools that are increasingly part of our daily life are the cameras, from webcams to integrated smartphone cameras. In order to fully use and exploit these technologies, the disciplines of Computer Vision and especially Deep Learning will help, allowing to analyze video streams and predict their content and meaning, exactly as if a human being were watching them.
FERRARETTI, Denis. « Data Mining for Petroleum Geology ». Doctoral thesis, Università degli studi di Ferrara, 2012. http://hdl.handle.net/11392/2389427.
Texte intégralLongo, Eugenio. « AI e IoT : contesto e stato dell’arte ». Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Trouver le texte intégralALTIERI, ALEX. « Yacht experience, ricerca e sviluppo di soluzioni basate su intelligenza artificiale per il comfort e la sicurezza in alto mare ». Doctoral thesis, Università Politecnica delle Marche, 2021. http://hdl.handle.net/11566/287605.
Texte intégralThe thesis describes the results of the research and development of new technologies based on artificial intelligence techniques, able to achieve an empathic interaction and an emotional connection between man and "the machines" in order to improve comfort and safety on board of yachts. This interaction is achieved through the recognition of emotions and behaviors and the following activation of all those multimedia devices available in the environment on board, which are adapted to the mood of the subject inside the room. The prototype system developed during the three years of PhD is now able to manage multimedia content (e.g. music tracks, videos played on LED screens) and light scenarios, based on the user's emotion, recognized by facial expressions taken from any camera installed inside the space. In order to make the interaction adaptive, the developed system implements Deep Learning algorithms to recognize the identity of the users on board (Facial Recognition), the degree of attention of the commander (Gaze Detection and Drowsiness) and the objects with which he interacts (phone, earphones, etc.). This information is processed within the system to identify any situations of risk to the safety of people on board and to monitor the entire environment. The application of these technologies, in this domain that is always open to the introduction of the latest innovations on board, opens up several research challenges.
PAREJO, MATOS ANTONIO. « Application of Intelligent Techniques for Optimal Management of Weakly Connected Microgrids ». Doctoral thesis, Università degli studi di Genova, 2022. http://hdl.handle.net/11567/1081257.
Texte intégralThe decarbonization and the climate change mitigation have become a priority for many countries and governments. One of the main tools for accomplishing these objectives is the growth of renewable generation sources in the power system, but their inclusion constitutes a great challenge for the network operation due to their high variability and their stochastic behavior. In this context, the management of the power system and microgrids can be treated as optimization problems in which the resources are operated with the aim of minimizing the cost function. This cost function and the corresponding operative restrictions depend on each specific situation, for example, on which are the power consumption requirements, how weak is the connection with the power grid, and how critical are the loads to be fed in the zone. In this sense, despite the large variety of optimization approaches, these have in common the importance of counting on a high-quality forecasting system for predicting the uncertainties of the microgrid (or network) to operate. The main existing approaches for predicting the uncertainties are deterministic and stochastic (which in many cases is also called probabilistic) forecasting. Considering the importance of forecasting systems for performing the optimization of microgrids and, in general, power networks, this doctoral thesis is focused on the design of a microgrid-oriented forecasting framework that includes a wide range of forecasting approaches, which makes possible its integration with other applications, for example, energy management optimization systems. This framework includes several deterministic and stochastic methods and is able to handle the training and selection of the models for performing the forecast according to the type of uncertainty representation that is required in each case.
La descarbonización y la reducción del cambio climático se han convertido en una prioridad para muchos países y gobiernos. Una de las principales herramientas para lograr estos objetivos es aumentar el número de fuentes de generación renovables en el sistema eléctrico, pero su inclusión constituye un gran reto debido a su alta variabilidad y su comportamiento estocástico. En este contexto, la gestión del sistema eléctrico y de las microrredes puede tratarse como problemas de optimización en los que los recursos se operan con el objetivo de minimizar la función de coste. Esta función de coste y las correspondientes restricciones operativas dependen de cada situación concreta, por ejemplo, de cuáles sean las necesidades de consumo de energía, de lo débil que sea la conexión con la red eléctrica y de lo críticas que sean las cargas a alimentar en la zona. En este sentido, a pesar de la gran variedad de enfoques de optimización, éstos tienen en común la importancia de contar con un sistema de predicción de alta calidad para predecir las incertidumbres de la microrred (o red) a optimizar. Los principales enfoques existentes para predecir las incertidumbres son la predicción determinista y la estocástica (que en muchos casos también se denomina probabilística). Teniendo en cuenta la importancia de los sistemas de predicción para realizar la optimización de las microrredes y, en general, de las redes eléctricas, esta tesis doctoral se centra en el diseño de un marco de trabajo para predicción orientado a las microrredes que incluye diversos enfoques para realizar la predicción, lo que hace posible su integración con otras aplicaciones como, por ejemplo, sistemas de optimización de gestión energética. Este marco de trabajo incluye varios métodos deterministas y estocásticos y es capaz de gestionar el entrenamiento y la selección de los modelos para realizar la predicción según el tipo de representación de la incertidumbre que se requiera en cada caso.
CALANNA, PIERPAOLO. « Investigazione di alcuni fenomeni di response bias nei questionari self-report mediante algoritmi di apprendimento automatico ». Doctoral thesis, 2020. http://hdl.handle.net/11573/1348128.
Texte intégralFRATTALE, MASCIOLI Fabio Massimo. « Algoritmi Costruttivi di Apprendimento per Reti Neurali ». Doctoral thesis, 1995. http://hdl.handle.net/11573/630577.
Texte intégralPARISI, Raffaele. « Algoritmi di apprendimento veloci per reti neurali multistrato ». Doctoral thesis, 1995. http://hdl.handle.net/11573/389747.
Texte intégralLofaro, Danilo, Domenico Conforti et Rosita Guido. « Modelli integrati di analisi di sopravvivenza applicati alla prognosi del trapianto renale ». Thesis, 2013. http://hdl.handle.net/10955/901.
Texte intégralFiorentini, Nicholas. « Intelligent solutions for supporting decision-making processes in road management : A general framework accounting for environment, road serviceability, and user’s safety ». Doctoral thesis, 2022. http://hdl.handle.net/2158/1279821.
Texte intégralTriggiani, Maurizio. « Integration of machine learning techniques in chemometrics practices ». Doctoral thesis, 2022. http://hdl.handle.net/11589/237998.
Texte intégralFrancalanci, Lucia. « Proposta di un metodo di valutazione automatica della leggibilità di pagine web in lingua italiana ». Doctoral thesis, 2019. http://hdl.handle.net/2158/1218395.
Texte intégral