Дисертації з теми "Factorization system"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Factorization system.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Factorization system".
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.
1
Agagu, Tosin. "Recommendation Approaches Using Context-Aware Coupled Matrix Factorization." Thesis, Université d'Ottawa / University of Ottawa, 2017. http://hdl.handle.net/10393/37012.
Повний текст джерелаАнотація:
In general, recommender systems attempt to estimate user preference based on historical data. A context-aware recommender system attempts to generate better recommendations using contextual information. However, generating recommendations for specific contexts has been challenging because of the difficulties in using contextual information to enhance the capabilities of recommender systems.
Several methods have been used to incorporate contextual information into traditional recommendation algorithms. These methods focus on incorporating contextual information to improve general recommendations for users rather than identifying the different context applicable to the user and providing recommendations geared towards those specific contexts.
In this thesis, we explore different context-aware recommendation techniques and present our context-aware coupled matrix factorization methods that use matrix factorization for estimating user preference and features in a specific contextual condition.
We develop two methods: the first method attaches user preference across multiple contextual conditions, making the assumption that user preference remains the same, but the suitability of items differs across different contextual conditions; i.e., an item might not be suitable for certain conditions. The second method assumes that item suitability remains the same across different contextual conditions but user preference changes. We perform a number of experiments on the last.fm dataset to evaluate our methods. We also compared our work to other context-aware recommendation approaches. Our results show that grouping ratings by context and jointly factorizing with common factors improves prediction accuracy.
2
Tabari, Michel, and Rawand Sultani. "A comparison of matrix factorization algorithms for a movie recommender system." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-229734.
Повний текст джерелаАнотація:
Recommendation systems is a growing technique for providing a better user experience for discovering new content on a platform. It can be implemented in many contexts such as Netflix for recommending movies. There are many ways to implement recommendation systems. This paper investigated two of these methods - Weighted Alternating Least Squares and Stochastic Gradient Descent - which fall into the category of matrix factorization and measured their performance in regards to time taken for training, error convergence and prediction quality. To our help we have used TensorFlow, a machine learning framework developed by Google which have been providing us with algorithms, models for training, and testing. The results showed that the Weighted Alternating Least Squares model proved to be better in terms of prediction quality: We also found that the quality of our predictions relied heavily on the model's parameters, since optimal predictions for a model can be found through the correct tuning. We concluded that the choice of model depends heavily on the data set investigated, and that optimal parameters for one model cannot simply be transferred to another model.Rekommendationssystem används alltmer för att förbättra användarupplevelser. Dessa kan implementeras i många sammanhang som i streamingplattformen Netflix för att rekommendera filmer till sina användare. Det finns många sätt att implementera rekommendationssystem och i denna rapport undersöktes två av dessa metoder - Weighted Alternating Least Squares och Stochastic Gradient Descent - som ligger inom kategorin av matrisfaktorisering och deras diverse prestandamått som träningstid, felkonvergens samt kvalitén på förslagen. Till vår hjälp användes TensorFlow, ett ramverk för maskininlärning som utvecklats av Google som har tillhandahållit oss modeller och algoritmer. Resultatet var att Weighted Alternating Least Squares modellen visade sig vara bättre med avseende på kvalitén på förslagen och vi fann även att kvalitén var starkt beroende av modellens parametrar, då vi fann att optimala förslag för en modell kan hittas genom korrekt justering av dessa parametrar. Vi drog slutsatsen att valet av modell beror på den data som undersöks och att optimala parametrar för en modell inte direkt kan överföras till en annan.
3
Winck, Ryder Christian. "Simultaneous control of coupled actuators using singular value decomposition and semi-nonnegative matrix factorization." Diss., Georgia Institute of Technology, 2012. http://hdl.handle.net/1853/45907.
Повний текст джерелаАнотація:
This thesis considers the application of singular value decomposition (SVD) and semi-nonnegative matrix factorization (SNMF) within feedback control systems, called the SVD System and SNMF System, to control numerous subsystems with a reduced number of control inputs. The subsystems are coupled using a row-column structure to allow mn subsystems to be controlled using m+n inputs. Past techniques for controlling systems in this row-column structure have focused on scheduling procedures that offer limited performance. The SVD and SNMF Systems permit simultaneous control of every subsystem, which increases the convergence rate by an order of magnitude compared with previous methods. In addition to closed loop control, open loop procedures using the SVD and SNMF are compared with previous scheduling procedures, demonstrating significant performance improvements. This thesis presents theoretical results for the controllability of systems using the row-column structure and for the stability and performance of the SVD and SNMF Systems. Practical challenges to the implementation of the SVD and SNMF Systems are also examined. Numerous simulation examples are provided, in particular, a dynamic simulation of a pin array device, called Digital Clay, and two physical demonstrations are used to assess the feasibility of the SVD and SNMF Systems for specific applications.
4
Goda, Sai Bharath. "Recommender system for recipes." Thesis, Kansas State University, 2014. http://hdl.handle.net/2097/17741.
Повний текст джерелаАнотація:
Master of ScienceDepartment of Computing and Information Sciences
Daniel A. Anderson
Most of the e-commerce websites like Amazon, EBay, hotels, trip advisor etc. use recommender systems to recommend products to their users. Some of them use the knowledge of history/ of all users to recommend what kind of products the current user may like (Collaborative filtering) and some use the knowledge of the products which the user is interested in and make recommendations (Content based filtering). An example is Amazon which uses both kinds of techniques.. These recommendation systems can be represented in the form of a graph where the nodes are users and products and edges are between users and products. The aim of this project is to build a recommender system for recipes by using the data from allrecipes.com. Allrecipes.com is a popular website used all throughout the world to post recipes, review them and rate them. To understand the data set one needs to know how the recipes are posted and rated in allrecipes.com, whose details are given in the paper. The network of allrecipes.com consists of users, recipes and ingredients. The aim of this research project is to extensively study about two algorithms adsorption and matrix factorization, which are evaluated on homogeneous networks and try them on the heterogeneous networks and analyze their results. This project also studies another algorithm that is used to propagate influence from one network to another network. To learn from one network and propagate the same information to another network we compute flow (influence of one network on another) as described in [7]. The paper introduces a variant of adsorption that takes the flow values into account and tries to make recommendations in the user-recipe and the user-ingredient networks. The results of this variant are analyzed in depth in this paper.
5
Hedlund, Jesper, and Tengstrand Emma Nilsson. "A Comparison between Different Recommender System Approaches for a Book and an Author Recommender System." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166378.
Повний текст джерелаАнотація:
A recommender system is a popular tool used by companies to increase customer satisfaction and to increase revenue. Collaborative filtering and content-based filtering are the two most common approaches when implementing a recommender system, where the former provides recommendations based on user behaviour, and the latter uses the characteristics of the items that are recommended. The aim of the study was to develop and compare different recommender system approaches, for both book and author recommendations and their ability to predict user ratings of an e-book application. The evaluation of the models was done by measuring root mean square error (RMSE) and mean absolute error (MAE). Two pure models were developed, one based on collaborative filtering and one based on content-based filtering. Also, three different hybrid models using a combination of the two pure approaches were developed and compared to the pure models. The study also explored how aggregation of book data to author level could be used to implement an author recommender system. The results showed that the aggregated author data was more difficult to predict. However, it was difficult to draw any conclusions of the performance on author data due to the data aggregation. Although it was clear that it was possible to derive author recommendations based on data from books. The study also showed that the collaborative filtering model performed better than the content-based filtering model according to RMSE but not according to MAE. The lowest RMSE and MAE, however, were achieved by combining the two approaches in a hybrid model.
6
Broman, Nils. "Comparasion of recommender systems for stock inspiration." Thesis, Linköpings universitet, Programvara och system, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176408.
Повний текст джерелаАнотація:
Recommender systems are apparent in our lives through multiple different ways, such asrecommending what items to purchase when online shopping, recommending movies towatch and recommending restaurants in your area. This thesis aims to apply the sametechniques of recommender systems on a new area, namely stock recommendations basedon your current portfolio. The data used was collected from a social media platform forinvestments, Shareville, and contained multiple users portfolios. The implicit data wasthen used to train matrix factorization models, and the state-of-the-art LightGCN model.Experiments regarding different data splits was also conducted. Results indicate that rec-ommender systems techniques can be applied successfully to generate stock recommen-dations. Also, that the relative performance of the models on this dataset are in line withprevious research. LightGCN greatly outperforms matrix factorization models on this pro-posed dataset. The results also show that different data splits also greatly impact the re-sults, which is discussed in further detail in this thesis.
7
Sundaramurthy, Roshni. "Recommender System for Gym Customers." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166147.
Повний текст джерелаАнотація:
Recommender systems provide new opportunities for retrieving personalized information on the Internet. Due to the availability of big data, the fitness industries are now focusing on building an efficient recommender system for their end-users. This thesis investigates the possibilities of building an efficient recommender system for gym users. BRP Systems AB has provided the gym data for evaluation and it consists of approximately 896,000 customer interactions with 8 features. Four different matrix factorization methods, Latent semantic analysis using Singular value decomposition, Alternating least square, Bayesian personalized ranking, and Logistic matrix factorization that are based on implicit feedback are applied for the given data. These methods decompose the implicit data matrix of user-gym group activity interactions into the product of two lower-dimensional matrices. They are used to calculate the similarities between the user and activity interactions and based on the score, the top-k recommendations are provided. These methods are evaluated by the ranking metrics such as Precision@k, Mean average precision (MAP) @k, Area under the curve (AUC) score, and Normalized discounted cumulative gain (NDCG) @k. The qualitative analysis is also performed to evaluate the results of the recommendations. For this specific dataset, it is found that the optimal method is the Alternating least square method which achieved around 90\% AUC for the overall system and managed to give personalized recommendations to the users.
8
Johansson, Angela. "Distributed System for Factorisation of Large Numbers." Thesis, Linköping University, Department of Electrical Engineering, 2004. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1883.
Повний текст джерелаАнотація:
This thesis aims at implementing methods for factorisation of large numbers. Seeing that there is no deterministic algorithm for finding the prime factors of a given number, the task proves rather difficult. Luckily, there have been developed some effective probabilistic methods since the invention of the computer so that it is now possible to factor numbers having about 200 decimal digits. This however consumes a large amount of resources and therefore, virtually all new factorisations are achieved using the combined power of many computers in a distributed system.
The nature of the distributed system can vary. The original goal of the thesis was to develop a client/server system that allows clients to carry out a portion of the overall computations and submit the result to the server.
Methods for factorisation discussed for implementation in the thesis are: the quadratic sieve, the number field sieve and the elliptic curve method. Actually implemented was only a variant of the quadratic sieve: the multiple polynomial quadratic sieve (MPQS).
9
Nguyen, Le Ha Vy. "Stability and stabilization of several classes of fractional systems with delays." Thesis, Paris 11, 2014. http://www.theses.fr/2014PA112387/document.
Повний текст джерелаАнотація:
Nous considérons deux classes de systèmes fractionnaires linéaires invariants dans le temps avec des ordres commensurables et des retards discrets. La première est composée de systèmes fractionnaires à entrées multiples et à une sortie avec des retards en entrées ou en sortie. La seconde se compose de systèmes fractionnaires de type neutre avec retards commensurables. Nous étudions la stabilisation de la première classe de systèmes à l'aide de l'approche de factorisation. Nous obtenons des factorisations copremières à gauche et à droite et les facteurs de Bézout associés: ils permettent de constituer l'ensemble des contrôleurs stabilisants. Pour la deuxième classe de systèmes, nous nous sommes intéressés au cas critique où certaines chaînes de pôles sont asymptotiques à l'axe imaginaire. Tout d'abord, nous réalisons une approximation des pôles asymptotiques afin de déterminer leur emplacement par rapport à l'axe. Le cas échéant, des conditions nécessaires et suffisantes de stabilité H-infini sont données. Cette analyse de stabilité est ensuite étendue aux systèmes à retard classiques ayant la même forme. Enfin, nous proposons une approche unifiée pour les deux classes de systèmes à retards commensurables de type neutre (standards et fractionnaires). Ensuite, la stabilisation d'une sous-classe de systèmes neutres fractionnaires est étudiée. Premièrement, l'ensemble de tous les contrôleurs stabilisants est obtenu. Deuxièmement, nous prouvons que pour une grande classe de contrôleurs fractionnaires à retards il est impossible d'éliminer dans la boucle fermée les chaînes de pôles asymptotiques à l'axe imaginaire si de telles chaînes sont présentes dans les systèmes à contrôlerWe consider two classes of linear time-invariant fractional systems with commensurate orders and discrete delays. The first one consists of multi-input single-output fractional systems with output or input delays. The second one consists of single-input single-output fractional neutral systems with commensurate delays. We study the stabilization of the first class of systems using the factorization approach. We derive left and right coprime factorizations and Bézout factors, which are the elements to constitute the set of all stabilizing controllers. For the second class of systems, we are interested in the critical case where some chains of poles are asymptotic to the imaginary axis. First, we approximate asymptotic poles in order to determine their location relative to the axis. Then, when appropriate, necessary and sufficient conditions for H-infinity-stability are derived. This stability analysis is then extended to classical delay systems of the same form and finally a unified approach for both classes of neutral delay systems with commensurate delays (standard and fractional) is proposed. Next, the stabilization of a subclass of fractional neutral systems is studied. First, the set of all stabilizing controllers is derived. Second, we prove that a large class of fractional controllers with delays cannot eliminate in the closed loop chains of poles asymptotic to the imaginary axis if such chains are present in the controlled systems
10
Kišac, Matej. "Distribuované aplikace s využitím frameworku Windows Communication Foundation." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2016. http://www.nusl.cz/ntk/nusl-242060.
Повний текст джерелаАнотація:
This thesis deals with distributed applications and WCF framework. The first part is based on theoretical information about distributed systems and we also concentrate on models of distributed systems. Next part describes WCF framework and key elements of WCF application. The following chapter is designated to introduce information about prime factorization. Then the knowledge from previous parts is used to create examples of service-oriented applications. In conclusion we discuss main parts of designing distributed application to solve factorization problem. Finally the comparison of distributed and dedicated application is made.
11
Campos, Ludio Edson da Silva. "Um estudo sobre fatorações de matrizes e a resolução de sistemas lineares." [s.n.], 2008. http://repositorio.unicamp.br/jspui/handle/REPOSIP/306088.
Повний текст джерелаАнотація:
Orientador: Maria Zoraide Martins Costa SoaresDissertação (mestrado profissional) - Universidade Estadual de Campinas, Instituto de Matematica, Estatistica e Computação Cientifica
Made available in DSpace on 2018-08-10T23:10:07Z (GMT). No. of bitstreams: 1 Campos_LudioEdsondaSilva_M.pdf: 1007258 bytes, checksum: 78308663e7f18b51bedeb284cadca66a (MD5) Previous issue date: 2008
Resumo: Neste trabalho abordamos algumas fatorações de matrizes, com vistas à resolução de sistemas lineares através de métodos diretos. Enfocamos particularmente as decomposições LU, Cholesky e QR, cujo uso tem sido largamente difundido em implementações computacionais. Nosso objetivo é apresentar um texto didático, acessível a alunos de graduação, que contemple a teoria básica de cada fatoração, incluindo a demonstração dos principais resultados, e que também forneça condições para uma primeira implementação de cada decomposição. Sugerimos alguns algoritmos, que foram implementados no software livre OCTAVE, através dos quais comparamos o tempo gasto para resolução de alguns sistemas lineares, utilizando as fatorações citadas
Abstract: In this work we discuss some matrix factorizations, with a view to the resolution of linear systems through direct methods. We focus particularly the LU, Cholesky and QR decompositions, whose use has been widely spread in computer implementations. Our goal is to present a didactic text, accessible to undergraduate students, which contemplates the basic theory of each factorization, including the demonstration of the main result and that also provide conditions for a first implementation of each decomposition. We suggest some algorithms that were scheduled in the free software OCTAVE, through which we compare the time elapsed for the resolution of a few linear systems, using the factorizations cited.
Mestrado
Algebra linear
Mestre em Matemática
12
Backlund, Alexander. "Switching hybrid recommender system to aid the knowledge seekers." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-414623.
Повний текст джерелаАнотація:
In our daily life, time is of the essence. People do not have time to browse through hundreds of thousands of digital items every day to find the right item for them. This is where a recommendation system shines. Tigerhall is a company that distributes podcasts, ebooks and events to subscribers. They are expanding their digital content warehouse which leads to more data for the users to filter. To make it easier for users to find the right podcast or the most exciting e-book or event, a recommendation system has been implemented. A recommender system can be implemented in many different ways. There are content-based filtering methods that can be used that focus on information about the items and try to find relevant items based on that. Another alternative is to use collaboration filtering methods that use information about what the consumer has previously consumed in correlation with what other users have consumed to find relevant items. In this project, a hybrid recommender system that uses a k-nearest neighbors algorithm alongside a matrix factorization algorithm has been implemented. The k-nearest neighbors algorithm performed well despite the sparse data while the matrix factorization algorithm performs worse. The matrix factorization algorithm performed well when the user has consumed plenty of items.
13
Lee, Eun-Joo. "Accurate and Robust Preconditioning Techniques for Solving General Sparse Linear Systems." UKnowledge, 2008. http://uknowledge.uky.edu/gradschool_diss/650.
Повний текст джерела
14
North, Paige Randall. "Type theoretic weak factorization systems." Thesis, University of Cambridge, 2017. https://www.repository.cam.ac.uk/handle/1810/265152.
Повний текст джерелаАнотація:
This thesis presents a characterization of those categories with weak factorization systems that can interpret the theory of intensional dependent type theory with Σ, Π, and identity types. We use display map categories to serve as models of intensional dependent type theory. If a display map category (C, D) models Σ and identity types, then this structure generates a weak factorization system (L, R). Moreover, we show that if the underlying category C is Cauchy complete, then (C, R) is also a display map category modeling Σ and identity types (as well as Π types if (C, D) models Π types). Thus, our main result is to characterize display map categories (C, R) which model Σ and identity types and where R is part of a weak factorization system (L, R) on the category C. We offer three such characterizations and show that they are all equivalent when C has all finite limits. The first is that the weak factorization system (L, R) has the properties that L is stable under pullback along R and all maps to a terminal object are in R. We call such weak factorization systems type theoretic. The second is that the weak factorization system has what we call an Id-presentation: it can be built from certain categorical structure in the same way that a model of Σ and identity types generates a weak factorization system. The third is that the weak factorization system (L, R) is generated by a Moore relation system. This is a technical tool used to establish the equivalence between the first and second characterizations described. To conclude the thesis, we describe a certain class of convenient categories of topological spaces (a generalization of compactly generated weak Hausdorff spaces). We then construct a Moore relation system within these categories (and also within the topological topos) and thus show that these form display map categories with Σ and identity types (as well as Π types in the topological topos).
15
Parambath, Shameem Ahamed Puthiya. "Matrix Factorization Methods for Recommender Systems." Thesis, Umeå universitet, Institutionen för datavetenskap, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-74181.
Повний текст джерелаАнотація:
This thesis is a comprehensive study of matrix factorization methods used in recommender systems. We study and analyze the existing models, specifically probabilistic models used in conjunction with matrix factorization methods, for recommender systems from a machine learning perspective. We implement two different methods suggested in scientific literature and conduct experiments on the prediction accuracy of the models on the Yahoo! Movies rating dataset.
16
Merkel, Wolfgang. "Factorization of numbers with physical systems." [S.l. : s.n.], 2007. http://nbn-resolving.de/urn:nbn:de:bsz:289-vts-59347.
Повний текст джерела
17
Strömqvist, Zakris. "Matrix factorization in recommender systems : How sensitive are matrix factorization models to sparsity?" Thesis, Uppsala universitet, Statistiska institutionen, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-352653.
Повний текст джерелаАнотація:
One of the most popular methods in recommender systems are matrix factorization (MF) models. In this paper, the sensitivity of sparsity of these models are investigated using a simulation study. Using the MovieLens dataset as a base several dense matrices are created. These dense matrices are then made sparse in two different ways to simulate different kinds of data. The accuracy of MF is then measured on each of the simulated sparse matrices. This shows that the matrix factorization models are sensitive to the degree of information available. For high levels of sparsity the MF performs badly but as the information level increases the accuracy of the models improve, for both samples.
18
Gráca, Martin. "Neuronové sítě pro doporučování knih." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2018. http://www.nusl.cz/ntk/nusl-385949.
Повний текст джерелаАнотація:
This thesis deals with the field of recommendation systems using deep neural networks and their use in book recommendation. There are the main traditional recommender systems analysed and their representations are summarized, as well as systems with more advanced techniques based on machine learning. The core of the thesis is to use convolutional neural networks for natural language processing and create a hybrid book recommendation system. Suggested system includes matrix factorization and make recommendation based on user ratings and book metadata, including texts descriptions. I designed two models, one with bag-of-words technique and one with convolutional neural network. Both of them defeat baseline methods. On the created data set, that was created from the Goodreads, model with CNN beats model with BOW.
19
Jikuya, Ichiro, and Ichijo Hodaka. "A Floquet-like factorization for linear periodic systems." IEEE, 2009. http://hdl.handle.net/2237/13921.
Повний текст джерела
20
Lopez, Jose Elias. "Structurally constrained control systems using a factorization approach." Thesis, Massachusetts Institute of Technology, 1993. http://hdl.handle.net/1721.1/12213.
Повний текст джерелаАнотація:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1994.Includes bibliographical references (leaves 122-129).
by Jose Elias Lopez.
Ph.D.
21
Ching, Bryan. "OPTIMIZING LEMPEL-ZIV FACTORIZATION FOR THE GPU ARCHITECTURE." DigitalCommons@CalPoly, 2014. https://digitalcommons.calpoly.edu/theses/1238.
Повний текст джерелаАнотація:
Lossless data compression is used to reduce storage requirements, allowing for the relief of I/O channels and better utilization of bandwidth. The Lempel-Ziv lossless compression algorithms form the basis for many of the most commonly used compression schemes. General purpose computing on graphic processing units (GPGPUs) allows us to take advantage of the massively parallel nature of GPUs for computations other that their original purpose of rendering graphics. Our work targets the use of GPUs for general lossless data compression. Specifically, we developed and ported an algorithm that constructs the Lempel-Ziv factorization directly on the GPU. Our implementation bypasses the sequential nature of the LZ factorization and attempts to compute the factorization in parallel. By breaking down the LZ factorization into what we call the PLZ, we are able to outperform the fastest serial CPU implementations by up to 24x and perform comparatively to a parallel multicore CPU implementation. To achieve these speeds, our implementation outputted LZ factorizations that were on average only 0.01 percent greater than the optimal solution that what could be computed sequentially.
We are also able to reevaluate the fastest GPU suffix array construction algorithm, which is needed to compute the LZ factorization. We are able to find speedups of up to 5x over the fastest CPU implementations.
22
CASTRO, GUSTAVO AYRES DE. "AN APPROACH TO CONTROL OF NONLINEAR SYSTEMS THROUGH COPRIME FACTORIZATION." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 1998. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=9402@1.
Повний текст джерелаАнотація:
CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICOO trabalho apresenta uma teoria de fatorações coprimas para sistemas não lineares e aplicações dessa teoria em problemas de controle. A parte inicial é exatamente a teoria de fatorações coprimas, que se assemelha à versão linear. O problema da estabilização de sistemas não lineares é resolvido através de realimentação aditiva, com pré e pós compensadores dinâmicos não lineares. A solução para esse problema é dada na forma da classe de compensadores que estabilizam o sistema. São também apresentadas condições para a estabilidade na presença de ruídos aditivos. Outro problema bastante relevante do ponto de vista de controles é o da especificação da dinâmica do sistema de malha fechada. O enfoque apresenta soluções de caráter local, o que permite que a dinâmica a ser especificada seja definida apenas sobre uma restrição do espeço de entrada. Dessa forma tornou-se factível a especificação de dinâmicas dentro de uma classe relativamente ampla. São discutidas possibilidades para o problema da regulação. Também utilizando condiçòes locais é apresentada uma teoria de estabilização robusta com relação a perturbações não estruturadas. Algumas soluções explícitas e relativamente estruturadas são apresentadas.
The control of nonlinear systems via coprime factorization is the subject of this dissertation. Initially, a broad theory concerning nonlinear factorizations is presented. The class of stabilizing controllers for a given nonlinear plant is derived using that theory. Then, there are derived sufficient conditions for the closed loop system are also presented. One of the major departures from the original work on nonlinear factorizations is the fact that the solutions presented need only to be locally derived, which allows a wider class of dynamics to be assigned for the closed loop input- output transference relation. The robust control of nonlinear systems is achieved through the use of locally defined solutions, allowing to control systems subject to some relatively structured perturbations.
23
Sinani, Klajdi. "Iterative Rational Krylov Algorithm for Unstable Dynamical Systems and Genaralized Coprime Factorizations." Thesis, Virginia Tech, 2016. http://hdl.handle.net/10919/64425.
Повний текст джерелаАнотація:
Generally, large-scale dynamical systems pose tremendous computational difficulties when applied in numerical simulations. In order to overcome these challenges we use several model reduction techniques. For stable linear models these techniques work very well and provide good approximations for the full model. However, large-scale unstable systems arise in many applications. Many of the known model reduction methods are not very robust, or in some cases, may not even work if we are dealing with unstable systems. When approximating an unstable sytem by a reduced order model, accuracy is not the only concern. We also need to consider the structure of the reduced order model. Often, it is important that the number of unstable poles in the reduced system is the same as the number of unstable poles in the original system. The Iterative Rational Krylov Algorithm (IRKA) is a robust model reduction technique which is used to locally reduce stable linear dynamical systems optimally in the $mathcal{H}_2$-norm. While we cannot guarantee that IRKA reduces an unstable model optimally, there are no numerical obstacles to the reduction of an unstable model via IRKA. In this thesis, we investigate IRKA's behavior when it is used to reduce unstable models. We also consider systems for which we cannot obtain a first order realization of the transfer function. We can use Realization-independent IRKA to obtain a reduced order model which does not preserve the structure of the original model. In this paper, we
implement a structure preserving algorithm for systems with nonlinear frequency dependency.Master of Science
24
Hogg, Jonathan David. "High performance Cholesky and symmetric indefinite factorizations with applications." Thesis, University of Edinburgh, 2010. http://hdl.handle.net/1842/4892.
Повний текст джерелаАнотація:
The process of factorizing a symmetric matrix using the Cholesky (LLT ) or indefinite (LDLT ) factorization of A allows the efficient solution of systems Ax = b when A is symmetric. This thesis describes the development of new serial and parallel techniques for this problem and demonstrates them in the setting of interior point methods. In serial, the effects of various scalings are reported, and a fast and robust mixed precision sparse solver is developed. In parallel, DAG-driven dense and sparse factorizations are developed for the positive definite case. These achieve performance comparable with other world-leading implementations using a novel algorithm in the same family as those given by Buttari et al. for the dense problem. Performance of these techniques in the context of an interior point method is assessed.
25
Xarez, Isabel Margarida da Costa Andrade. "Reflections of universal algebras into semilattices, their Galois theories, and related factorization systems." Doctoral thesis, Universidade de Aveiro, 2013. http://hdl.handle.net/10773/11367.
Повний текст джерелаАнотація:
Doutoramento em MatemáticaEstabelecemos uma condição suficiente para a preservação dos produtos finitos, pelo reflector de uma variedade de álgebras universais numa subvariedade, que é, também, condição necessária se a subvariedade for idempotente. Esta condição é estabelecida, seguidamente, num contexto mais geral e caracteriza reflexões para as quais a propriedade de ser semi-exacta à esquerda e a propriedade, mais forte, de ter unidades estáveis, coincidem. Prova-se que reflexões simples e semi-exactas à esquerda coincidem, no contexto das variedades de álgebras universais e caracterizam-se as classes do sistema de factorização derivado da reflexão. Estabelecem-se resultados que ajudam a caracterizar morfismos de cobertura e verticais-estáveis em álgebras universais e no contexto mais geral já referido. Caracterizam-se as classes de morfismos separáveis, puramente inseparáveis e normais. O estudo dos morfismos de descida de Galois conduz a condições suficientes para que o seu par kernel seja preservado pelo reflector.
We begin with a sufficient condition for the preservation of finite products by a reflector from a variety of universal algebras into a subvariety, which is also a necessary condition when the subvariety is idempotent. This condition is then stated in a more general setting and this characterizes reflections for which semileftexactness and the stronger stable units property are the same. It is shown that simple and semi-left-exact reflections coincide in the context of varieties of universal algebras, and characterizations of the classes of the derived reflective factorization system are given. Several statements help then to characterize covering and stably-vertical morphisms of universal algebras, and in the more general setting referred to above. The classes of separable, purely inseparable and normal morphisms are characterized as well. The study of Galois descent morphisms provides conditions under which their kernel pairs are preserved by the reflector.
26
Holländer, John. "Investigating the performance of matrix factorization techniques applied on purchase data for recommendation purposes." Thesis, Malmö högskola, Fakulteten för teknik och samhälle (TS), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20624.
Повний текст джерелаАнотація:
Automated systems for producing product recommendations to users is a relatively new area within the field of machine learning. Matrix factorization techniques have been studied to a large extent on data consisting of explicit feedback such as ratings, but to a lesser extent on implicit feedback data consisting of for example purchases.The aim of this study is to investigate how well matrix factorization techniques perform compared to other techniques when used for producing recommendations based on purchase data. We conducted experiments on data from an online bookstore as well as an online fashion store, by running algorithms processing the data and using evaluation metrics to compare the results. We present results proving that for many types of implicit feedback data, matrix factorization techniques are inferior to various neighborhood- and association rules techniques for producing product recommendations. We also present a variant of a user-based neighborhood recommender system algorithm \textit{(UserNN)}, which in all tests we ran outperformed both the matrix factorization algorithms and the k-nearest neighbors algorithm regarding both accuracy and speed. Depending on what dataset was used, the UserNN achieved a precision approximately 2-22 percentage points higher than those of the matrix factorization algorithms, and 2 percentage points higher than the k-nearest neighbors algorithm. The UserNN also outperformed the other algorithms regarding speed, with time consumptions 3.5-5 less than those of the k-nearest neighbors algorithm, and several orders of magnitude less than those of the matrix factorization algorithms.
27
Fujimoto, Kenji. "Synthesis and Analysis of Nonlinear Control Systems Based on Transformations and Factorizations." 京都大学 (Kyoto University), 2001. http://hdl.handle.net/2433/151484.
Повний текст джерела
28
Magolu, Monga-Made. "Sparse approximate block factorizations for solving symmetric positive (semi)definite linear systems." Doctoral thesis, Universite Libre de Bruxelles, 1992. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/212924.
Повний текст джерела
29
Wu, Min. "On solutions of linear functional systems and factorization of modules over Laurent-Ore algebras." Nice, 2005. http://www.theses.fr/2005NICE4026.
Повний текст джерела
30
Sokal, Bruno. "Semi-blind receivers for multi-relaying mimo systems using rank-one tensor factorizations." reponame:Repositório Institucional da UFC, 2017. http://www.repositorio.ufc.br/handle/riufc/25988.
Повний текст джерелаАнотація:
SOKAL, B. Semi-blind receivers for multi-relaying mimo systems using rank-one tensor factorizations. 2017. 85 f. Dissertação (Mestrado em Engenharia de Teleinformática)-Centro de Tecnologia, Universidade Federal do Ceará, Fortaleza, 2017.Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-15T20:38:29Z No. of bitstreams: 1 2017_dis_bsokal.pdf: 1689224 bytes, checksum: f0e2e9424de721f23bf0629ba55330c1 (MD5)
Rejected by Marlene Sousa (mmarlene@ufc.br), reason: Prezado Bruno: Existe uma orientação para que normalizemos as dissertações e teses da UFC, em suas paginas pré-textuais e lista de referencias, pelas regras da ABNT. Por esse motivo, sugerimos consultar o modelo de template, para ajudá-lo nesta tarefa, disponível em: http://www.biblioteca.ufc.br/educacao-de-usuarios/templates/ Vamos agora as correções sempre de acordo com o template: 1. As informações da capa, folha de rosto (que segue a capa) e ficha catalográfica devem ser em língua portuguesa, mesmo que sua dissertação esteja em língua inglesa. A partir da folha de aprovação, devem ser em língua inglesa. 2. Exemplificando a capa, as informações que devem aparecer são pela ordem (Toadas em Maiúsculo e negrito): Nome da universidade, do centro, do departamento e nome do programa; Nome do aluno; Título; Cidade e data. 2. A folha de rosto também tem informações que não são necessárias. Consulte o template para ver uso de maiúsculas, negrito e ordem de apresentação das informações. 3. A ficha catalográfica deve vir antes da folha de aprovação e não depois desta. 4. A folha de aprovação não deve ter as informações do quadro no alto da folha, nem deve ser em negrito. Veja modelo no template. 5. De acordo com a ABNT mesmo escrita em outro idioma, primeiro coloca-se o resumo na língua portuguesa e depois o Abstract. As palavras RESUMO e ABSTRCT vem ser em caixa alta, negrito e no centro da folha. Não devem iniciar com paragrafo. Essa folhas são contadas mas não numeradas. Só a partir da introdução é que são numeradas. 6. Veja no template a ordem das folhas a partir dos agradecimentos e como devem ser apresentadas. 7. Na lista de figuras mantenha o mesmo espaço entre as linhas. 8. O sumário não deve conter as informações anteriores a INTRODUÇÃO, deve ser em negrito e sem recuo de paragrafo. Observe o uso de Caixa alta, itálico nas seções. Após a conclusão devem vir os APÊNDICES e as REFERENCIAS. 9. Na lista de referencias, pela ABNT, deve-se iniciar pelo sobrenome do autor, seguido do prenome. Elaboramos ferramentas para ajuda-lo a gerar as referencias e gerenciadores bibliográficos disponivel em: http://www.biblioteca.ufc.br/ferramentas-de-pesquisa/ Em artigos de revistas usa-se a seguinte nomenclatura para volume, numero e páginas: v. , n. , p. Não se destacam subtítulos e nos artigos de revistas se destaca-se apenas o ´nome da revista. Att. Marlene Rocha 3366-9620 mmarlene@ufc.br on 2017-09-18T11:38:11Z (GMT)
Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-20T14:04:25Z No. of bitstreams: 1 2017_dis_bsokal.pdf: 1481998 bytes, checksum: bdf4f504f50622f6b0e2084361272481 (MD5)
Approved for entry into archive by Marlene Sousa (mmarlene@ufc.br) on 2017-09-21T17:44:15Z (GMT) No. of bitstreams: 1 2017_dis_bsokal.pdf: 1481998 bytes, checksum: bdf4f504f50622f6b0e2084361272481 (MD5)
Made available in DSpace on 2017-09-21T17:44:15Z (GMT). No. of bitstreams: 1 2017_dis_bsokal.pdf: 1481998 bytes, checksum: bdf4f504f50622f6b0e2084361272481 (MD5) Previous issue date: 2017-07-27
Cooperative communications have shown to be an alternative to combat the impairments of signal propagation in wireless communications, such as path loss and shadowing, creating a virtual array of antennas for the source. In this work, we start with a two-hop MIMO system using a a single relay. By adding a space-time filtering step at the receiver, we propose a rank-one tensor factorization model for the resulting signal. Exploiting this model, two semi-blind receivers for joint symbol and channel estimation are derived: i) an iterative receiver based on the trilinear alternating least squares (Tri-ALS) algorithm and ii) a closed-form receiver based on the truncated higher order SVD (T-HOSVD). For this system, we also propose a space-time coding tensor having a PARAFAC decomposition structure, which gives more flexibility to system design, while allowing an orthogonal coding. In the second part of this work, we present an extension of the rank-one factorization approach to a multi-relaying scenario and a closed-form semi-blind receiver based on coupled SVDs (C-SVD) is derived. The C-SVD receiver efficiently combines all the available cooperative links to enhance channel and symbol estimation performance, while enjoying a parallel implementation.
Comunicações cooperativas têm mostrado ser uma alternativa para combater os efeitos de propagação do sinal em comunicações sem-fio, como, por exemplo, a perda por percurso e sombreamento, criando um array virtual de antenas para a fonte transmissora. Neste trabalho, toma-se como ponto de partida um modelo de sistema MIMO de dois saltos com um único relay. Adicionando um estágio de filtragem no receptor, é proposta uma fatoração de rank-um para o sinal resultante. A partir deste modelo, dois receptores semi-cegos para estimação conjunta de símbolo e canal são propostos: i) um receptor iterativo baseado no algoritmo trilinear de mínimos quadrados alternados (Tri-ALS) e ii) um receptor de solução fechada baseado na SVD de ordem superior truncada (T-HOSVD). Para este sistema, é também proposto um tensor de codificação espacial-temporal com uma estrutura PARAFAC, o que permite maior flexibilidade de design do sistema, além de uma codificação ortogonal. Na segunda parte deste trabalho, é apresentada uma extensão da fatoração de rank-um para o cenário multi-relay e um receptor semi-cego de solução fechada baseado em SVD's acopladas (C-SVD) é desenvolvido. O receptor C-SVD combina de modo eficiente todos os links cooperativos disponíveis, melhorando o desempenho da estimação de símbolos e de canal, além de oferecer uma implementação paralelizável.
31
Ercan, Eda. "Probabilistic Matrix Factorization Based Collaborative Filtering With Implicit Trust Derived From Review Ratings Information." Master's thesis, METU, 2010. http://etd.lib.metu.edu.tr/upload/12612529/index.pdf.
Повний текст джерела
32
Häger, Alexander. "Contextualizing music recommendations : A collaborative filtering approach using matrix factorization and implicit ratings." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167068.
Повний текст джерелаАнотація:
Recommender systems are helpful tools employed abundantly in online applications to help users find what they want. This thesis re-purposes a collaborative filtering recommender built for incorporating social media (hash)tags to be used as a context-aware recommender, using time of day and activity as contextual factors. The recommender uses a matrix factorization approach for implicit feedback, in a music streaming setting. Contextual data is collected from users' mobile phones while they are listening to music. It is shown in an offline test that this approach improves recall when compared to a recommender that does not account for the context the user was in. Future work should explore the qualities of this model further, as well as investigate how this model's recommendations can be surfaced in an application.
33
Yao, Sirui. "Evaluating, Understanding, and Mitigating Unfairness in Recommender Systems." Diss., Virginia Tech, 2021. http://hdl.handle.net/10919/103779.
Повний текст джерелаАнотація:
Recommender systems are information filtering tools that discover potential matchings between users and items and benefit both parties. This benefit can be considered a social resource that should be equitably allocated across users and items, especially in critical domains such as education and employment. Biases and unfairness in recommendations raise both ethical and legal concerns. In this dissertation, we investigate the concept of unfairness in the context of recommender systems. In particular, we study appropriate unfairness evaluation metrics, examine the relation between bias in recommender models and inequality in the underlying population, as well as propose effective unfairness mitigation approaches.
We start with exploring the implication of fairness in recommendation and formulating unfairness evaluation metrics. We focus on the task of rating prediction. We identify the insufficiency of demographic parity for scenarios where the target variable is justifiably dependent on demographic features. Then we propose an alternative set of unfairness metrics that measured based on how much the average predicted ratings deviate from average true ratings. We also reduce these unfairness in matrix factorization (MF) models by explicitly adding them as penalty terms to learning objectives.
Next, we target a form of unfairness in matrix factorization models observed as disparate model performance across user groups. We identify four types of biases in the training data that contribute to higher subpopulation error. Then we propose personalized regularization learning (PRL), which learns personalized regularization parameters that directly address the data biases. PRL poses the hyperparameter search problem as a secondary learning task. It enables back-propagation to learn the personalized regularization parameters by leveraging the closed-form solutions of alternating least squares (ALS) to solve MF. Furthermore, the learned parameters are interpretable and provide insights into how fairness is improved.
Third, we conduct theoretical analysis on the long-term dynamics of inequality in the underlying population, in terms of the fitting between users and items. We view the task of recommendation as solving a set of classification problems through threshold policies. We mathematically formulate the transition dynamics of user-item fit in one step of recommendation. Then we prove that a system with the formulated dynamics always has at least one equilibrium, and we provide sufficient conditions for the equilibrium to be unique. We also show that, depending on the item category relationships and the recommendation policies, recommendations in one item category can reshape the user-item fit in another item category.
To summarize, in this research, we examine different fairness criteria in rating prediction and recommendation, study the dynamic of interactions between recommender systems and users, and propose mitigation methods to promote fairness and equality.Doctor of Philosophy
Recommender systems are information filtering tools that discover potential matching between users and items. However, a recommender system, if not properly built, may not treat users and items equitably, which raises ethical and legal concerns. In this research, we explore the implication of fairness in the context of recommender systems, study the relation between unfairness in recommender output and inequality in the underlying population, and propose effective unfairness mitigation approaches. We start with finding unfairness metrics appropriate for recommender systems. We focus on the task of rating prediction, which is a crucial step in recommender systems. We propose a set of unfairness metrics measured as the disparity in how much predictions deviate from the ground truth ratings. We also offer a mitigation method to reduce these forms of unfairness in matrix factorization models Next, we look deeper into the factors that contribute to error-based unfairness in matrix factorization models and identify four types of biases that contribute to higher subpopulation error. Then we propose personalized regularization learning (PRL), which is a mitigation strategy that learns personalized regularization parameters to directly addresses data biases. The learned per-user regularization parameters are interpretable and provide insight into how fairness is improved. Third, we conduct a theoretical study on the long-term dynamics of the inequality in the fitting (e.g., interest, qualification, etc.) between users and items. We first mathematically formulate the transition dynamics of user-item fit in one step of recommendation. Then we discuss the existence and uniqueness of system equilibrium as the one-step dynamics repeat. We also show that depending on the relation between item categories and the recommendation policies (unconstrained or fair), recommendations in one item category can reshape the user-item fit in another item category. In summary, we examine different fairness criteria in rating prediction and recommendation, study the dynamics of interactions between recommender systems and users, and propose mitigation methods to promote fairness and equality.
34
NÓBREGA, Caio Santos Bezerra. "Uma estratégia para predição da taxa de aprendizagem do gradiente descendente para aceleração da fatoração de matrizes." Universidade Federal de Campina Grande, 2014. http://dspace.sti.ufcg.edu.br:8080/jspui/handle/riufcg/362.
Повний текст джерелаАнотація:
Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-04-11T14:50:08Z
No. of bitstreams: 1
CAIO SANTOS BEZERRA NÓBREGA - DISSERTAÇÃO PPGCC 2014..pdf: 983246 bytes, checksum: 5eca7651706ce317dc514ec2f1aa10c3 (MD5)Made available in DSpace on 2018-04-11T14:50:08Z (GMT). No. of bitstreams: 1 CAIO SANTOS BEZERRA NÓBREGA - DISSERTAÇÃO PPGCC 2014..pdf: 983246 bytes, checksum: 5eca7651706ce317dc514ec2f1aa10c3 (MD5) Previous issue date: 2014-07-30
Capes
Sugerir os produtos mais apropriados aos diversos tipos de consumidores não é uma tarefa trivial, apesar de ser um fator chave para aumentar satisfação e lealdade destes. Devido a esse fato, sistemas de recomendação têm se tornado uma ferramenta importante para diversas aplicações, tais como, comércio eletrônico, sites personalizados e redes sociais. Recentemente, a fatoração de matrizes se tornou a técnica mais bem sucedida de implementação de sistemas de recomendação. Os parâmetros do modelo de fatoração de matrizes são tipicamente aprendidos por meio de métodos numéricos, tal como o gradiente descendente. O desempenho do gradiente descendente está diretamente relacionada à configuração da taxa de aprendizagem, a qual é tipicamente configurada para valores pequenos, com o objetivo de não perder um mínimo local. Consequentemente, o algoritmo pode levar várias iterações para convergir. Idealmente,é desejada uma taxa de aprendizagem que conduza a um mínimo local nas primeiras iterações, mas isto é muito difícil de ser realizado dada a alta complexidade do espaço de valores a serem pesquisados. Começando com um estudo exploratório em várias bases de dados de sistemas de recomendação, observamos que, para a maioria das bases, há um padrão linear entre a taxa de aprendizagem e o número de iterações necessárias para atingir a convergência. A partir disso, propomos utilizar modelos de regressão lineares simples para predizer, para uma base de dados desconhecida, um bom valor para a taxa de aprendizagem inicial. A ideia é estimar uma taxa de aprendizagem que conduza o gradiente descendenteaummínimolocalnasprimeirasiterações. Avaliamosnossatécnicaem8bases desistemasderecomendaçãoreaisecomparamoscomoalgoritmopadrão,oqualutilizaum valorfixoparaataxadeaprendizagem,ecomtécnicasqueadaptamataxadeaprendizagem extraídas da literatura. Nós mostramos que conseguimos reduzir o número de iterações até em 40% quando comparados à abordagem padrão.
Suggesting the most suitable products to different types of consumers is not a trivial task, despite being a key factor for increasing their satisfaction and loyalty. Due to this fact, recommender systems have be come an important tool for many applications, such as e-commerce, personalized websites and social networks. Recently, Matrix Factorization has become the most successful technique to implement recommendation systems. The parameters of this model are typically learned by means of numerical methods, like the gradient descent. The performance of the gradient descent is directly related to the configuration of the learning rate, which is typically set to small values, in order to do not miss a local minimum. As a consequence, the algorithm may take several iterations to converge. Ideally, one wants to find a learning rate that will lead to a local minimum in the early iterations, but this is very difficult to achieve given the high complexity of search space. Starting with an exploratory study on several recommendation systems datasets, we observed that there is an over all linear relationship between the learnin grate and the number of iterations needed until convergence. From this, we propose to use simple linear regression models to predict, for a unknown dataset, a good value for an initial learning rate. The idea is to estimate a learning rate that drives the gradient descent as close as possible to a local minimum in the first iteration. We evaluate our technique on 8 real-world recommender datasets and compared it with the standard Matrix Factorization learning algorithm, which uses a fixed value for the learning rate over all iterations, and techniques fromt he literature that adapt the learning rate. We show that we can reduce the number of iterations until at 40% compared to the standard approach.
35
Ingverud, Patrik. "Complexity evaluation of CNNs in tightly coupled hybrid recommender systems." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-232027.
Повний текст джерелаАнотація:
In this report we evaluated how the complexity of a Convolutional Neural Network (CNN), in terms of number of filters, size of filters and dropout, affects the performance on the rating prediction accuracy in a tightly coupled hybrid recommender system. We also evaluated the effect on the rating prediction accuracy for pretrained CNNs in comparison to non-pretrained CNNs. We found that a less complex model, i.e. smaller filters and less number of filters, showed trends of better performance. Less regularization, in terms of dropout, had trends of better performance for the less complex models. Regarding the comparison of the pretrained models and non-pretrained models the experimental results were almost identical for the two denser datasets while pretraining had slightly worse performance on the sparsest dataset.I denna rapport utvärderade vi komplexiteten på ett neuralt faltningsnätverk (eng. Convolutional Neural Network) i form av antal filter, storleken på filtren och regularisering, i form av avhopp (eng. dropout), för att se hur dessa hyperparametrar påverkade träffsäkerheten för rekommendationer i ett hybridrekommendationssystem. Vi utvärderade även hur förträning av det neurala faltningsnätverket påverkade träffsäkerheten för rekommendationer i jämförelse med ett icke förtränat neuralt faltningsnätverk. Resultaten visade trender på att en mindre komplex modell, det vill säga mindre och färre filter, gav bättre resultat. Även mindre regularisering, i form av avhopp, gav bättre resultat för mindre komplexa modeller. Gällande jämförelsen med förtränade modeller och icke förtränade modeller visade de experimentella resultaten nästan ingen skillnad för de två kompaktare dataseten medan förträning gav lite sämre resultat på det glesaste datasetet.
36
Dias, Pedro Ricardo Gomes. "Recommending media content based on machine learning methods." Master's thesis, Faculdade de Ciências e Tecnologia, 2011. http://hdl.handle.net/10362/6581.
Повний текст джерелаАнотація:
Dissertação para obtenção do Grau de Mestre em
Engenharia InformáticaInformation is nowadays made available and consumed faster than ever before. This information technology generation has access to a tremendous deal of data and is left with the heavy burden of choosing what is relevant. With the increasing growth of media sources, the amount of content made available to users has become overwhelming and in need to be managed. Recommender systems emerged with the purpose of providing personalized and meaningful content recommendations based on users’ preferences and usage history. Due to their utility and commercial potential, recommender systems integrate many audiovisual content providers and represent one of their most important and valuable services. The goal of this thesis is to develop a recommender system based on matrix factorization methods, capable of providing meaningful and personalized product recommendations to individual users and groups of users, by taking into account users’ rating patterns and biased tendencies, as well as their fluctuations throughout time.
37
Zeng, Jingying. "Latent Factor Models for Recommender Systems and Market Segmentation Through Clustering." The Ohio State University, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=osu1491255524283942.
Повний текст джерела
38
Parimi, Rohit. "Collaborative filtering approaches for single-domain and cross-domain recommender systems." Diss., Kansas State University, 2015. http://hdl.handle.net/2097/20108.
Повний текст джерелаАнотація:
Doctor of PhilosophyComputing and Information Sciences
Doina Caragea
Increasing amounts of content on the Web means that users can select from a wide variety of items (i.e., items that concur with their tastes and requirements). The generation of personalized item suggestions to users has become a crucial functionality for many web applications as users benefit from being shown only items of potential interest to them. One popular solution to creating personalized item suggestions to users is recommender systems. Recommender systems can address the item recommendation task by utilizing past user preferences for items captured as either explicit or implicit user feedback. Numerous collaborative filtering (CF) approaches have been proposed in the literature to address the recommendation problem in the single-domain setting (user preferences from only one domain are used to recommend items). However, increasingly large datasets often prevent experimentation of every approach in order to choose the one that best fits an application domain. The work in this dissertation on the single-domain setting studies two CF algorithms, Adsorption and Matrix Factorization (MF), considered to be state-of-the-art approaches for implicit feedback and suggests that characteristics of a domain (e.g., close connections versus loose connections among users) or characteristics of data available (e.g., density of the feedback matrix) can be useful in selecting the most suitable CF approach to use for a particular recommendation problem. Furthermore, for Adsorption, a neighborhood-based approach, this work studies several ways to construct user neighborhoods based on similarity functions and on community detection approaches, and suggests that domain and data characteristics can also be useful in selecting the neighborhood approach to use for Adsorption. Finally, motivated by the need to decrease computational costs of recommendation algorithms, this work studies the effectiveness of using short-user histories and suggests that short-user histories can successfully replace long-user histories for recommendation tasks. Although most approaches for recommender systems use user preferences from only one domain, in many applications, user interests span items of various types (e.g., artists and tags). Each recommendation problem (e.g., recommending artists to users or recommending tags to users) can be considered unique domains, and user preferences from several domains can be used to improve accuracy in one domain, an area of research known as cross-domain recommender systems. The work in this dissertation on cross-domain recommender systems investigates several limitations of existing approaches and proposes three novel approaches (two Adsorption-based and one MF-based) to improve recommendation accuracy in one domain by leveraging knowledge from multiple domains with implicit feedback. The first approach performs aggregation of neighborhoods (WAN) from the source and target domains, and the neighborhoods are used with Adsorption to recommend target items. The second approach performs aggregation of target recommendations (WAR) from Adsorption computed using neighborhoods from the source and target domains. The third approach integrates latent user factors from source domains into the target through a regularized latent factor model (CIMF). Experimental results on six target recommendation tasks from two real-world applications suggest that the proposed approaches effectively improve target recommendation accuracy as compared to single-domain CF approaches and successfully utilize varying amounts of user overlap between source and target domains. Furthermore, under the assumption that tuning may not be possible for large recommendation problems, this work proposes an approach to calculate knowledge aggregation weights based on network alignment for WAN and WAR approaches, and results show the usefulness of the proposed solution. The results also suggest that the WAN and WAR approaches effectively address the cold-start user problem in the target domain.
39
Martin, Andrew John. "A High Performance Parallel Sparse Linear Equation Solver Using CUDA." Kent State University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=kent1310603635.
Повний текст джерела
40
Wang, Xiwei. "Data Privacy Preservation in Collaborative Filtering Based Recommender Systems." UKnowledge, 2015. http://uknowledge.uky.edu/cs_etds/35.
Повний текст джерелаАнотація:
This dissertation studies data privacy preservation in collaborative filtering based recommender systems and proposes several collaborative filtering models that aim at preserving user privacy from different perspectives.
The empirical study on multiple classical recommendation algorithms presents the basic idea of the models and explores their performance on real world datasets. The algorithms that are investigated in this study include a popularity based model, an item similarity based model, a singular value decomposition based model, and a bipartite graph model. Top-N recommendations are evaluated to examine the prediction accuracy.
It is apparent that with more customers' preference data, recommender systems can better profile customers' shopping patterns which in turn produces product recommendations with higher accuracy. The precautions should be taken to address the privacy issues that arise during data sharing between two vendors. Study shows that matrix factorization techniques are ideal choices for data privacy preservation by their nature. In this dissertation, singular value decomposition (SVD) and nonnegative matrix factorization (NMF) are adopted as the fundamental techniques for collaborative filtering to make privacy-preserving recommendations. The proposed SVD based model utilizes missing value imputation, randomization technique, and the truncated SVD to perturb the raw rating data. The NMF based models, namely iAux-NMF and iCluster-NMF, take into account the auxiliary information of users and items to help missing value imputation and privacy preservation. Additionally, these models support efficient incremental data update as well.
A good number of online vendors allow people to leave their feedback on products. It is considered as users' public preferences. However, due to the connections between users' public and private preferences, if a recommender system fails to distinguish real customers from attackers, the private preferences of real customers can be exposed. This dissertation addresses an attack model in which an attacker holds real customers' partial ratings and tries to obtain their private preferences by cheating recommender systems. To resolve this problem, trustworthiness information is incorporated into NMF based collaborative filtering techniques to detect the attackers and make reasonably different recommendations to the normal users and the attackers. By doing so, users' private preferences can be effectively protected.
41
Herrmann, Julien. "Memory-aware Algorithms and Scheduling Techniques for Matrix Computattions." Thesis, Lyon, École normale supérieure, 2015. http://www.theses.fr/2015ENSL1043/document.
Повний текст джерелаАнотація:
Dans cette thèse, nous nous sommes penchés d’un point de vue à la foisthéorique et pratique sur la conception d’algorithmes et detechniques d’ordonnancement adaptées aux architectures complexes dessuperordinateurs modernes. Nous nous sommes en particulier intéressésà l’utilisation mémoire et la gestion des communications desalgorithmes pour le calcul haute performance (HPC). Nous avonsexploité l’hétérogénéité des superordinateurs modernes pour améliorerles performances du calcul matriciel. Nous avons étudié lapossibilité d’alterner intelligemment des étapes de factorisation LU(plus rapide) et des étapes de factorisation QR (plus stablenumériquement mais plus deux fois plus coûteuses) pour résoudre unsystème linéaire dense. Nous avons amélioré les performances desystèmes d’exécution dynamique à l’aide de pré-calculs statiquesprenants en compte l’ensemble du graphe de tâches de la factorisationCholesky ainsi que l’hétérogénéité de l’architecture. Nous noussommes intéressés à la complexité du problème d’ordonnancement degraphes de tâches utilisant de gros fichiers d’entrée et de sortiesur une architecture hétérogène avec deux types de ressources,utilisant chacune une mémoire spécifique. Nous avons conçu denombreuses heuristiques en temps polynomial pour la résolution deproblèmes généraux que l’on avait prouvés NP-complet aupréalable. Enfin, nous avons conçu des algorithmes optimaux pourordonnancer un graphe de différentiation automatique sur uneplateforme avec deux types de mémoire : une mémoire gratuite maislimitée et une mémoire coûteuse mais illimitéeThroughout this thesis, we have designed memory-aware algorithms and scheduling techniques suitedfor modern memory architectures. We have shown special interest in improving the performance ofmatrix computations on multiple levels. At a high level, we have introduced new numerical algorithmsfor solving linear systems on large distributed platforms. Most of the time, these linear solvers rely onruntime systems to handle resources allocation and data management. We also focused on improving thedynamic schedulers embedded in these runtime systems by adding static information to their decisionprocess. We proposed new memory-aware dynamic heuristics to schedule workflows, that could beimplemented in such runtime systems.Altogether, we have dealt with multiple state-of-the-art factorization algorithms used to solve linearsystems, like the LU, QR and Cholesky factorizations. We targeted different platforms ranging frommulticore processors to distributed memory clusters, and worked with several reference runtime systemstailored for these architectures, such as P A RSEC and StarPU. On a theoretical side, we took specialcare of modelling convoluted hierarchical memory architectures. We have classified the problems thatare arising when dealing with these storage platforms. We have designed many efficient polynomial-timeheuristics on general problems that had been shown NP-complete beforehand
42
Rouet, François-Henry. "Memory and performance issues in parallel multifrontal factorizations and triangular solutions with sparse right-hand sides." Thesis, Toulouse, INPT, 2012. http://www.theses.fr/2012INPT0070/document.
Повний текст джерелаАнотація:
Nous nous intéressons à la résolution de systèmes linéaires creux de très grande taille sur des machines parallèles. Dans ce contexte, la mémoire est un facteur qui limite voire empêche souvent l’utilisation de solveurs directs, notamment ceux basés sur la méthode multifrontale. Cette étude se concentre sur les problèmes de mémoire et de performance des deux phases des méthodes directes les plus coûteuses en mémoire et en temps : la factorisation numérique et la résolution triangulaire. Dans une première partie nous nous intéressons à la phase de résolution à seconds membres creux, puis, dans une seconde partie, nous nous intéressons à la scalabilité mémoire de la factorisation multifrontale. La première partie de cette étude se concentre sur la résolution triangulaire à seconds membres creux, qui apparaissent dans de nombreuses applications. En particulier, nous nous intéressons au calcul d’entrées de l’inverse d’une matrice creuse, où les seconds membres et les vecteurs solutions sont tous deux creux. Nous présentons d’abord plusieurs schémas de stockage qui permettent de réduire significativement l’espace mémoire utilisé lors de la résolution, dans le cadre d’exécutions séquentielles et parallèles. Nous montrons ensuite que la façon dont les seconds membres sont regroupés peut fortement influencer la performance et nous considérons deux cadres différents : le cas "hors-mémoire" (out-of-core) où le but est de réduire le nombre d’accès aux facteurs, qui sont stockés sur disque, et le cas "en mémoire" (in-core) où le but est de réduire le nombre d’opérations. Finalement, nous montrons comment améliorer le parallélisme. Dans la seconde partie, nous nous intéressons à la factorisation multifrontale parallèle. Nous montrons tout d’abord que contrôler la mémoire active spécifique à la méthode multifrontale est crucial, et que les technique de "répartition" (mapping) classiques ne peuvent fournir une bonne scalabilité mémoire : le coût mémoire de la factorisation augmente fortement avec le nombre de processeurs. Nous proposons une classe d’algorithmes de répartition et d’ordonnancement "conscients de la mémoire" (memory-aware) qui cherchent à maximiser la performance tout en respectant une contrainte mémoire fournie par l’utilisateur. Ces techniques ont révélé des problèmes de performances dans certains des noyaux parallèles denses utilisés à chaque étape de la factorisation, et nous avons proposé plusieurs améliorations algorithmiques. Les idées présentées tout au long de cette étude ont été implantées dans le solveur MUMPS (Solveur MUltifrontal Massivement Parallèle) et expérimentées sur des matrices de grande taille (plusieurs dizaines de millions d’inconnues) et sur des machines massivement parallèles (jusqu’à quelques milliers de coeurs). Elles ont permis d’améliorer les performances et la robustesse du code et seront disponibles dans une prochaine version. Certaines des idées présentées dans la première partie ont également été implantées dans le solveur PDSLin (solveur linéaire hybride basé sur une méthode de complément de Schur)We consider the solution of very large sparse systems of linear equations on parallel architectures. In this context, memory is often a bottleneck that prevents or limits the use of direct solvers, especially those based on the multifrontal method. This work focuses on memory and performance issues of the two memory and computationally intensive phases of direct methods, that is, the numerical factorization and the solution phase. In the first part we consider the solution phase with sparse right-hand sides, and in the second part we consider the memory scalability of the multifrontal factorization. In the first part, we focus on the triangular solution phase with multiple sparse right-hand sides, that appear in numerous applications. We especially emphasize the computation of entries of the inverse, where both the right-hand sides and the solution are sparse. We first present several storage schemes that enable a significant compression of the solution space, both in a sequential and a parallel context. We then show that the way the right-hand sides are partitioned into blocks strongly influences the performance and we consider two different settings: the out-of-core case, where the aim is to reduce the number of accesses to the factors, that are stored on disk, and the in-core case, where the aim is to reduce the computational cost. Finally, we show how to enhance the parallel efficiency. In the second part, we consider the parallel multifrontal factorization. We show that controlling the active memory specific to the multifrontal method is critical, and that commonly used mapping techniques usually fail to do so: they cannot achieve a high memory scalability, i.e. they dramatically increase the amount of memory needed by the factorization when the number of processors increases. We propose a class of "memory-aware" mapping and scheduling algorithms that aim at maximizing performance while enforcing a user-given memory constraint and provide robust memory estimates before the factorization. These techniques have raised performance issues in the parallel dense kernels used at each step of the factorization, and we have proposed some algorithmic improvements. The ideas presented throughout this study have been implemented within the MUMPS (MUltifrontal Massively Parallel Solver) solver and experimented on large matrices (up to a few tens of millions unknowns) and massively parallel architectures (up to a few thousand cores). They have demonstrated to improve the performance and the robustness of the code, and will be available in a future release. Some of the ideas presented in the first part have also been implemented within the PDSLin (Parallel Domain decomposition Schur complement based Linear solver) solver
43
Thapa, Nirmal. "CONTEXT AWARE PRIVACY PRESERVING CLUSTERING AND CLASSIFICATION." UKnowledge, 2013. http://uknowledge.uky.edu/cs_etds/15.
Повний текст джерелаАнотація:
Data are valuable assets to any organizations or individuals. Data are sources of useful information which is a big part of decision making. All sectors have potential to benefit from having information. Commerce, health, and research are some of the fields that have benefited from data. On the other hand, the availability of the data makes it easy for anyone to exploit the data, which in many cases are private confidential data. It is necessary to preserve the confidentiality of the data. We study two categories of privacy: Data Value Hiding and Data Pattern Hiding. Privacy is a huge concern but equally important is the concern of data utility. Data should avoid privacy breach yet be usable. Although these two objectives are contradictory and achieving both at the same time is challenging, having knowledge of the purpose and the manner in which it will be utilized helps. In this research, we focus on some particular situations for clustering and classification problems and strive to balance the utility and privacy of the data.
In the first part of this dissertation, we propose Nonnegative Matrix Factorization (NMF) based techniques that accommodate constraints defined explicitly into the update rules. These constraints determine how the factorization takes place leading to the favorable results. These methods are designed to make alterations on the matrices such that user-specified cluster properties are introduced. These methods can be used to preserve data value as well as data pattern. As NMF and K-means are proven to be equivalent, NMF is an ideal choice for pattern hiding for clustering problems. In addition to the NMF based methods, we propose methods that take into account the data structures and the attribute properties for the classification problems. We separate the work into two different parts: linear classifiers and nonlinear classifiers. We propose two different solutions based on the classifiers. We study the effect of distortion on the utility of data.
We propose three distortion measurement metrics which demonstrate better characteristics than the traditional metrics. The effectiveness of the measures is examined on different benchmark datasets. The result shows that the methods have the desirable properties such as invariance to translation, rotation, and scaling.
44
Fathollahzadeh, Pedram. "Improving Food Recipe Suggestions with Hierarchical Classification of Food Recipes." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-224782.
Повний текст джерелаАнотація:
Making personalized recommendations has become a central part in many platforms, and is continuing to grow with more access to massive amounts of data online. Giving recommendations based on the interests of the individual, rather than recommending items that are popular, increases the user experience and can potentially attract more customers when done right. In order to make personalized recommendations, many platforms resort to machine learning algorithms. In the context of food recipes, these machine learning algorithms tend to consist of hybrid methods between collaborative filtering, content-based methods and matrix factorization. Most content-based approaches are ingredient based and can be very fruitful. However, fetching every single ingredient for recipes and processing them can be computationally expensive. Therefore, this paper investigates if clustering recipes according to what cuisine they belong to and what the main protein is can also improve rating predictions compared to when only collaborative filtering and matrix factorization methods are employed. This suggested content-based approach has a structure of a hierarchical classification, where recipes are first clustered into what cuisine group they belong to, then the specific cuisine and finally what the main protein is. The results suggest that the content-based approach can improve the predictions slightly but not significantly, and can help reduce the sparsity of the rating matrix to some extent. However, it suffers from heavily sparse data with respect to how many rating predictions it can give.Att ge personliga rekommendationer har blivit en central del av många plattformar och fortsätter att bli det då tillgången till stora mängder data har ökat. Genom att ge personliga rekommendationer baserat på användares intressen, istället för att rekommendera det som är populärt, förbättrar användarupplevelsen och kan attrahera fler kunder. För att kunna producera personliga rekommendationer så vänder sig många plattformar till maskininlärningsalgoritmer. När det kommer till matrecept, så brukar dessa maskininlärningsalgoritmer bestå av hybrida metoder som sammanfogar collaborative filtering, innehållsbaserande metoder och matrisfaktorisering. De flesta innehållsbaserande metoderna baseras på ingredienser och har visats vara effektiva. Däremot, så kan det vara kostsamt för datorer att ta hänsyn till varenda ingrediens i varje matrecept. Därför undersöker denna artikel om att klassificera recept hierarkiskt efter matkultur och huvudprotein också kan förbättra rekommendationer när bara collaborative filtering och matrisfaktorisering används. Denna innehållsbaserande metod har en struktur av hierarkisk klassificering, där recept först indelas efter matkultur, specifik matkultur och till slut vad huvudproteinet är. Resultaten visar att innehållsbaserande metoden kan förbättra receptförslagen, men inte på en statistisk signifikant nivå, och kan reducera gleshet i en matris med tillsatta betyg från olika användare med olika recept något. Däremot så påverkas den ansenligt när det är glest med tillgänglighet av data.
Eatit
45
Lee, Joonseok. "Local approaches for collaborative filtering." Diss., Georgia Institute of Technology, 2015. http://hdl.handle.net/1853/53846.
Повний текст джерелаАнотація:
Recommendation systems are emerging as an important business application as the demand for personalized services in E-commerce increases. Collaborative filtering techniques are widely used for predicting a user's preference or generating a list of items to be recommended. In this thesis, we develop several new approaches for collaborative filtering based on model combination and kernel smoothing. Specifically, we start with an experimental study that compares a wide variety of CF methods under different conditions. Based on this study, we formulate a combination model similar to boosting but where the combination coefficients are functions rather than constant. In another contribution we formulate and analyze a local variation of matrix factorization. This formulation constructs multiple local matrix factorization models and then combines them into a global model. This formulation is based on the local low-rank assumption, a slightly different but more plausible assumption about the rating matrix. We apply this assumption to both rating prediction and ranking problems, with both empirical validations and theoretical analysis.
We contribute with this thesis in four aspects. First, the local approaches we present significantly improve the accuracy of recommendations both in rating prediction and ranking problems. Second, with the more realistic local low-rank assumption, we fundamentally change the underlying assumption for matrix factorization-based recommendation systems. Third, we present highly efficient and scalable algorithms which take advantage of parallelism, suited for recent large scale datasets. Lastly, we provide an open source software implementing the local approaches in this thesis as well as many other recent recommendation algorithms, which can be used both in research and production.
46
Guillou, Frédéric. "On recommendation systems in a sequential context." Thesis, Lille 3, 2016. http://www.theses.fr/2016LIL30041/document.
Повний текст джерелаАнотація:
Cette thèse porte sur l'étude des Systèmes de Recommandation dans un cadre séquentiel, où les retours des utilisateurs sur des articles arrivent dans le système l'un après l'autre. Après chaque retour utilisateur, le système doit le prendre en compte afin d'améliorer les recommandations futures. De nombreuses techniques de recommandation ou méthodologies d'évaluation ont été proposées par le passé pour les problèmes de recommandation. Malgré cela, l'évaluation séquentielle, qui est pourtant plus réaliste et se rapproche davantage du cadre d'évaluation d'un vrai système de recommandation, a été laissée de côté. Le contexte séquentiel nécessite de prendre en considération différents aspects non visibles dans un contexte fixe. Le premier de ces aspects est le dilemme dit d'exploration vs. exploitation: le modèle effectuant les recommandations doit trouver le bon compromis entre recueillir de l'information sur les goûts des utilisateurs à travers des étapes d'exploration, et exploiter la connaissance qu'il a à l'heure actuelle pour maximiser le feedback reçu. L'importance de ce premier point est mise en avant à travers une première évaluation, et nous proposons une approche à la fois simple et efficace, basée sur la Factorisation de Matrice et un algorithme de Bandit Manchot, pour produire des recommandations appropriées. Le second aspect pouvant apparaître dans le cadre séquentiel surgit dans le cas où une liste ordonnée d'articles est recommandée au lieu d'un seul article. Dans cette situation, le feedback donné par l'utilisateur est multiple: la partie explicite concerne la note donnée par l'utilisateur concernant l'article choisi, tandis que la partie implicite concerne les articles cliqués (ou non cliqués) parmi les articles de la liste. En intégrant les deux parties du feedback dans un modèle d'apprentissage, nous proposons une approche basée sur la Factorisation de Matrice, qui peut recommander de meilleures listes ordonnées d'articles, et nous évaluons cette approche dans un contexte séquentiel particulier pour montrer son efficacitéThis thesis is dedicated to the study of Recommendation Systems under a sequential setting, where the feedback given by users on items arrive one after another in the system. After each feedback, the system has to integrate it and try to improve future recommendations. Many techniques or evaluation methods have already been proposed to study the recommendation problem. Despite that, such sequential setting, which is more realistic and represent a closer framework to a real Recommendation System evaluation, has surprisingly been left aside. Under a sequential context, recommendation techniques need to take into consideration several aspects which are not visible for a fixed setting. The first one is the exploration-exploitation dilemma: the model making recommendations needs to find a good balance between gathering information about users' tastes or items through exploratory recommendation steps, and exploiting its current knowledge of the users and items to try to maximize the feedback received. We highlight the importance of this point through the first evaluation study and propose a simple yet efficient approach to make effective recommendation, based on Matrix Factorization and Multi-Armed Bandit algorithms. The second aspect emphasized by the sequential context appears when a list of items is recommended to the user instead of a single item. In such a case, the feedback given by the user includes two parts: the explicit feedback as the rating, but also the implicit feedback given by clicking (or not clicking) on other items of the list. By integrating both feedback into a Matrix Factorization model, we propose an approach which can suggest better ranked list of items, and we evaluate it in a particular setting
47
Donfack, Simplice. "Methods and algorithms for solving linear systems of equations on massively parallel computers." Thesis, Paris 11, 2012. http://www.theses.fr/2012PA112042.
Повний текст джерелаАнотація:
Les processeurs multi-cœurs sont considérés de nos jours comme l'avenir des calculateurs et auront un impact important dans le calcul scientifique. Cette thèse présente une nouvelle approche de résolution des grands systèmes linéaires creux et denses, qui soit adaptée à l'exécution sur les futurs machines pétaflopiques et en particulier celles ayant un nombre important de cœurs. Compte tenu du coût croissant des communications comparé au temps dont les processeurs mettent pour effectuer les opérations arithmétiques, notre approche adopte le principe de minimisation des communications au prix de quelques calculs redondants et utilise plusieurs adaptations pour atteindre de meilleures performances sur les machines multi-cœurs. Nous décomposons le problème à résoudre en plusieurs phases qui sont ensuite mises en œuvre séparément. Dans la première partie, nous présentons un algorithme basé sur le partitionnement d'hypergraphe qui réduit considérablement le remplissage ("fill-in") induit lors de la factorisation LU des matrices creuses non symétriques. Dans la deuxième partie, nous présentons deux algorithmes de réduction de communication pour les factorisations LU et QR qui sont adaptés aux environnements multi-cœurs. La principale contribution de cette partie est de réorganiser les opérations de la factorisation de manière à réduire la sollicitation du bus tout en utilisant de façon optimale les ressources. Nous étendons ensuite ce travail aux clusters de processeurs multi-cœurs. Dans la troisième partie, nous présentons une nouvelle approche d'ordonnancement et d'optimisation. La localité des données et l'équilibrage des charges représentent un sérieux compromis pour le choix des méthodes d'ordonnancement. Sur les machines NUMA par exemple où la localité des données n'est pas une option, nous avons observé qu'en présence de perturbations systèmes (" OS noise"), les performances pouvaient rapidement se dégrader et devenir difficiles à prédire. Pour cela, nous présentons une approche combinant un ordonnancement statique et dynamique pour ordonnancer les tâches de nos algorithmes. Nos résultats obtenues sur plusieurs architectures montrent que tous nos algorithmes sont efficaces et conduisent à des gains de performances significatifs. Nous pouvons atteindre des améliorations de l'ordre de 30 à 110% par rapport aux correspondants de nos algorithmes dans les bibliothèques numériques bien connues de la littératureMulticore processors are considered to be nowadays the future of computing, and they will have an important impact in scientific computing. In this thesis, we study methods and algorithms for solving efficiently sparse and dense large linear systems on future petascale machines and in particular these having a significant number of cores. Due to the increasing communication cost compared to the time the processors take to perform arithmetic operations, our approach embrace the communication avoiding algorithm principle by doing some redundant computations and uses several adaptations to achieve better performance on multicore machines.We decompose the problem to solve into several phases that would be then designed or optimized separately. In the first part, we present an algorithm based on hypergraph partitioning and which considerably reduces the fill-in incurred in the LU factorization of sparse unsymmetric matrices. In the second part, we present two communication avoiding algorithms that are adapted to multicore environments. The main contribution of this part is to reorganize the computations such as to reduce bus contention and using efficiently resources. Then, we extend this work for clusters of multi-core processors. In the third part, we present a new scheduling and optimization approach. Data locality and load balancing are a serious trade-off in the choice of the scheduling strategy. On NUMA machines for example, where the data locality is not an option, we have observed that in the presence of noise, performance could quickly deteriorate and become difficult to predict. To overcome this bottleneck, we present an approach that combines a static and a dynamic scheduling approach to schedule the tasks of our algorithms.Our results obtained on several architectures show that all our algorithms are efficient and lead to significant performance gains. We can achieve from 30 up to 110% improvement over the corresponding routines of our algorithms in well known libraries
48
Déhaye, Vincent. "Characterisation of a developer’s experience fields using topic modelling." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-171946.
Повний текст джерелаАнотація:
Finding the most relevant candidate for a position represents an ubiquitous challenge for organisations. It can also be arduous for a candidate to explain on a concise resume what they have experience with. Due to the fact that the candidate usually has to select which experience to expose and filter out some of them, they might not be detected by the person carrying out the search, whereas they were indeed having the desired experience. In the field of software engineering, developing one's experience usually leaves traces behind: the code one produced. This project explores approaches to tackle the screening challenges with an automated way of extracting experience directly from code by defining common lexical patterns in code for different experience fields, using topic modeling. Two different techniques were compared. On one hand, Latent Dirichlet Allocation (LDA) is a generative statistical model which has proven to yield good results in topic modeling. On the other hand Non-Negative Matrix Factorization (NMF) is simply a singular value decomposition of a matrix representing the code corpus as word counts per piece of code.The code gathered consisted of 30 random repositories from all the collaborators of the open-source Ruby-on-Rails project on GitHub, which was then applied common natural language processing transformation steps. The results of both techniques were compared using respectively perplexity for LDA, reconstruction error for NMF and topic coherence for both. The two first represent how well the data could be represented by the topics produced while the later estimates the hanging and fitting together of the elements of a topic, and can depict human understandability and interpretability. Given that we did not have any similar work to benchmark with, the performance of the values obtained is hard to assess scientifically. However, the method seems promising as we would have been rather confident in assigning labels to 10 of the topics generated. The results imply that one could probably use natural language processing methods directly on code production in order to extend the detected fields of experience of a developer, with a finer granularity than traditional resumes and with fields definition evolving dynamically with the technology.
49
Zarudniev, Mykhailo. "Synthèse de fréquence par couplage d'oscillateurs spintroniques." Phd thesis, Ecole Centrale de Lyon, 2013. http://tel.archives-ouvertes.fr/tel-00804561.
Повний текст джерелаАнотація:
La tendance actuelle dans le domaine des télécommunications mène à des systèmes capables de fonctionner selon plusieurs standards, et donc plusieurs fréquences porteuses. La synthèse de la fréquence porteuse est un élément clef, dont les propriétés reposent essentiellement sur les performances de l'oscillateur employé. Pour assurer le fonctionnement de systèmes compatibles avec plusieurs standards de télécommunication, la solution conventionnelle consiste à intégrer plusieurs oscillateurs locaux. Cette solution est coûteuse, d'autant plus que, malgré le fait que les technologies actuelles atteignent des niveaux d'intégration très importants, la surface occupée par des oscillateurs traditionnels de type LC ne peut pas être diminuée, alors que le coût de fabrication au millimètre carré devient de plus en plus élevé. Il serait donc très intéressant de remplacer les oscillateurs LC, ce qui nous amène à rechercher des solutions alternatives parmi de nouvelles technologies. L'oscillateur spintronique (STO) est un nouveau dispositif issu des études sur les couches minces magnétiques. Il apparait comme un candidat potentiel de remplacement des oscillateurs LC du fait de sa grande accordabilité en fréquence et de son faible encombrement. Toutefois des mesures effectuées sur les STOs ont montré que la performance en puissance et en bruit de phase d'un oscillateur seul ne permet pas de remplir les spécifications pour des applications de télécommunication. Nous proposons de remplir ces spécifications en couplant un nombre d'oscillateurs spintroniques important. Dans ce cadre se posent plusieurs questions qui concernent les procédures de modélisation, d'analyse et de synthèse des systèmes interconnectés. Les procédures de modélisation incluent la démarche de recherche de modèles à complexité croissante qui décrivent les propriétés entrée-sortie d'un oscillateur spintronique, ainsi que la démarche de généralisation des modèles des oscillateurs dans le cadre du réseau. Les procédures d'analyse cherchent à vérifier la stabilité et évaluer la performance des systèmes interconnectés. Les procédures de synthèse permettent de concevoir des interconnexions sophistiquées pour les oscillateurs afin d'assurer toutes les spécifications du cahier des charges. Dans ce document, nous établissons tout d'abord le problème de la synthèse de fréquence par couplage avec un cahier des charges formalisé en termes de gabarits fréquentiels sur des densités spectrales de puissance. Le cahier des charges posé amène la nécessité de modéliser l'oscillateur spintronique pour pouvoir simuler et analyser son comportement. Ici, nous proposons une modélisation originale selon des degrés de complexité croissante. Ensuite, nous discutons de la structure de la commande de l'ensemble des oscillateurs afin de remplir les spécifications du cahier des charges. La structure de commande proposée nécessite de développer une méthode de conception des interconnexions du réseau d'après les critères de performance. Dans les deux derniers chapitres, nous proposons deux méthodes fréquentielles de synthèse originales pour résoudre le problème de synthèse de fréquence par couplage. La première méthode de synthèse permet de prendre en compte un critère mathématique du cahier des charges, qui correspond à un gabarit fréquentiel à respecter, et permet d'obtenir une matrice d'interconnexion des sous-systèmes, telle que le module de la réponse fréquentielle du réseau approxime le gabarit imposé par le cahier des charges. La deuxième méthode de synthèse permet de prendre en compte plusieurs gabarits fréquentiels à la fois. La solution obtenue est une matrice d'interconnexion des sous-systèmes, qui résout le problème de la synthèse de fréquence par couplage d'oscillateurs spintroniques.
50
Jonsson, Isak. "Recursive Blocked Algorithms, Data Structures, and High-Performance Software for Solving Linear Systems and Matrix Equations." Doctoral thesis, Umeå : Univ, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-160.
Повний текст джерела