Contents
Academic literature on the topic 'Ottimizzazione stocastica'
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 'Ottimizzazione stocastica.'
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.
Dissertations / Theses on the topic "Ottimizzazione stocastica"
FRANCHINI, Giorgia. "Selezione degli iperparametri nei metodi di ottimizzazione stocastica." Doctoral thesis, Università degli studi di Modena e Reggio Emilia, 2021. http://hdl.handle.net/11380/1237616.
Full textIn the context of deep learning, the computational more expensive phase is the full training of the learning algorithm. Indeed the design of a new learning algorithm requires an extensive numerical investigation with the execution of a significant number of experimental trials. A fundamental aspect in designing a suitable learning algorithm is the selection of the hyperparameters (parameters that are not trained during the learning process), in a static or adaptive way. The aim of this thesis is to investigate the hyperparameters selection strategies on which standard machine learning algorithms are designed. In particular, we are interested in the different techniques to select the parameters related to the stochastic gradient methods used for training the machine learning methodologies. The main purposes that motivate this study are the improvement of the accuracy (or other metrics suitable for evaluating the inspected methodology) and the acceleration of the convergence rate of the iterative optimization schemes. To achieve these purposes, the analysis has mainly focused on the choice of the fundamental parameters (hyperparameters) in the stochastic gradient methods: the steplength, the minibatch size and the potential adoption of variance reduction techniques. In a first approach we considered separately the choice of steplength and minibatch size; then, we presented a technique that combines the two choices. About the steplength selection, we propose to tailor for the stochastic gradient iteration the steplength selection adopted in the full-gradient method known as Limited Memory Steepest Descent method. This strategy, based on the Ritz-like values of a suitable matrix, enables to give a local estimate of the inverse of the local Lipschitz parameter. Regarding the minibatch size the idea is to increasing dynamically, in an adaptive manner (based on suitable validation tests), this size. The experiments show that this training strategy is more efficient (in terms of time and costs) compared with the approaches available in literature. We combine the two parameter choices (steplength and minibatch size) in an adaptive scheme without introducing line search techniques, while the possible increase of the size of the subsample used to compute the stochastic gradient enables to control the variance of this direction. In the second part of the thesis, we introduce an Automatic Machine Learning (AutoML) technique to set these parameters. In particular, we propose a low-cost strategy to predict the accuracy of the learning algorithm, based only on its initial behavior. The initial and final accuracies observed during this beforehand process are stored in a database and used as training set of a Support Vector Machines learning algorithm. The aim is to predict the accuracy of a learning methodology, given its accuracy on the initial iterations of its learning process. In other word, by a probabilistic exploration of the hyperparameter space, we are able to find the setting providing optimal accuracies at a quite low cost. An extensive numerical experimentation was carried out involving convex and non-convex functions (in particular Convolutional Neural Networks). For the numerical experiments several datasets well known in literature have been used, for different problems such as: classification, segmentation, regression. Finally, a computational study is carried out to extend the proposed approaches to other methods, such as: Momentum, ADAM, SVRG. In conclusion, the contribution of the thesis consists in providing useful ideas about an effective and inexpensive selection of the hyperparameters in the class of the stochastic gradient methods.
Prevedello, Paolo. "Ottimizzazione stocastica di una microrete con tecnologia "vehicle-to-grid"." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016.
Find full textCarmignan, Silvia. "Metodo del gradiente stocastico in ricostruzione di immagini tomografiche." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16177/.
Full textFanigliulo, Claudio. "Valutazione su base stocastica dell'area contribuente al deflusso fluviale." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/15097/.
Full textMARELLA, ANDREA. "Metodi innovativi di monitoraggio e di analisi di dati di traffico per la soluzione di problemi di ottimizzazione stocastica di impianti semaforici coordinati." Doctoral thesis, Università degli studi di Genova, 2021. http://hdl.handle.net/11567/1034676.
Full textThe development of information technology and the implementation of smart city projects have made it possible in a few years to have an enormous amount of data. How to put this information to good use is the goal of this work. The field of Intelligent Transportation Systems (ITS) is one of the areas in which research on new data, combined with Artificial Intelligent (AI), has begun to show interesting results. ITS allows for the provision of innovative and advanced services relating to modes of transport and traffic management and allows users to make smarter choices when using transport networks. This has a direct effect on the effectiveness of the infrastructure in urban smart cities. Scientific research in the traffic and transport sector has made big data on traffic available directly with the need to study models of analysis and representation of data that go beyond the classic modeling (so-called simulation agent model based). Thanks to big data on traffic and AI and Machine Learning (ML) techniques, it is now possible to study new models for predicting the behavior of road users (so-called data-driven models). This work is intended to be a concrete example of the use of different innovative systems for monitoring traffic data, traffic models and optimization applied in a real case. The traffic light intersections analyzed were the subject of an aerial video monitoring campaign with innovative instrumentation, the application of computer vision software and traffic data processing, FCD data processing, and, finally, the resolution of a problem of stochastic programming for optimal coordination. In drafting the paper, since it was a mixed study of applied research and a real case, it was oriented as much as possible to maintaining a strong contact with the professional field and real applicability of the results.
Filippini, Mattia. "Magnetic gears numerical modelling and optimization." Doctoral thesis, Università degli studi di Padova, 2019. http://hdl.handle.net/11577/3425766.
Full textL'obiettivo principale di questa tesi è quello di fornire strategie di modellazione e ottimizzazione efficienti per un dispositivo elettromagnetico noto come ingranaggio magnetico. In particolare modelli magnetici, termici e meccanici sono esaminati includendo materiali non lineari, algoritmi di smagnetizzazione magneti permanenti e modelli di isteresi in nuclei laminati. Dal punto di vista della modellazione magnetica, un approccio analitico per la progettazione semplificata dell'ingranaggio è presentata. Particolare attenzione viene data all'onere computazionale del metodo che è particolarmente adatto alle procedure di ottimizzazione stocastica. Per l'analisi dettagliata degli ingranaggi magnetici, un algoritmo basato sull'accoppiamento Finite Element / Boundary Element viene proposto, comprese le non linearità ferromagnetiche, le equazioni differenziali meccaniche, correnti parassite ed equazioni circuitali. Modelli dettagliati sono introdotti e discussi per analizzare gli effetti dell'isteresi dei materiali dolci e magnetizzazione, smagnetizzazione e recoil di magneti permanenti. Vengono anche investigati i meccanismi di perdita negli ingranaggi magnetici e le perdite di trasmissione al variare delle velocità di rotazione e gli angoli di carico. Un modello meccanico semplificato dell'ingranaggio magnetico è presentato e formulato come un insieme dei vincoli di disuguaglianza, fornendo così un collegamento diretto alle strategie di ottimizzazione. I vincoli meccanici includono gli spostamenti e le sollecitazioni dei poli ferromagnetici e le limitazioni sulla velocità di rotazione dovuta a sforzi eccessivi, risonanze e vibrazioni. Un'analisi semplificata basata su una rete termica equivalente è presentato, nella quale si considera anche il flusso di raffreddamento assiale. Le tecniche di ottimizzazione stocastica sono discusse per una progettazione multi-fisica della macchina ottimizzata e il modello analitico è incorporato in uno schema di evoluzione differenziale. Infine, i risultati ottimizzati sono discussi e confrontati con le soluzioni meccaniche commerciali. Viene inoltre proposta e analizzata una soluzione basata sulla connessione delle barre assiali che garantiscono un effetto di smorzamento quando la marcia dell'ingranaggio diventa asincrona. Tutti gli algoritmi sono stati convalidati tramite confronto con codici commerciali o, quando possibile, con i dati di esperimenti recuperati dalla letteratura.
Chiriatti, Sara. "Implementazione di un modello stocastico per la simulazione di una microrete con tecnologia vehicle to grid." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/13949/.
Full textDi, Graziano Carla. "Metodi di ottimizzazione stocastici." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/15824/.
Full textSittoni, Pietro. "Un modello dinamico di ottimizzazione di portafoglio per robo-advisors." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23228/.
Full text