Now showing items 25776-25795 of 41446

    Learning multilingual and multimodal representations with language-specific encoders and decoders for machine translation 

    Escolano Peinado, Carlos (Date of defense: 2022-03-18)

    This thesis aims to study different language-specific approaches for Multilingual Machine Translation without parameter sharing and their properties compared to the current state-of-the-art based on parameter-sharing. We ...

    Learning of meaningful visual representations for continuous lip-reading 

    Fernández López, Adriana (Date of defense: 2021-03-04)

    In the last decades, there has been an increased interest in decoding speech exclusively using visual cues, i.e. mimicking the human capability to perform lip-reading, leading to Automatic Lip-Reading (ALR) systems. ...

    Learning patterns and social-emotional learning of balkan students in secondary education 

    Ahmedi, Shqiponjë (Date of defense: 2022-11-04)

    En el present estudi, es mesuren components relacionats amb els patrons d’aprenentatge i l’aprenentatge socioemocional en una mostra d’adolescents de la península dels Balcans, una regió postiugoslava que durant dècades ...

    Learning relational models with human interaction for planning in robotics 

    Martínez Martínez, David (Date of defense: 2017-02-21)

    Automated planning has proven to be useful to solve problems where an agent has to maximize a reward function by executing actions. As planners have been improved to salve more expressive and difficult problems, there is ...

    Learning representations for medical image diagnosis: impact of curriculum training and architectural design 

    Jiménez Sánchez, Amelia (Date of defense: 2021-10-14)

    This thesis investigates two key aspects of learning deep-based image representations for medical diagnosis. The two are confronted with common challenges of medical image databases, namely, the limited number of samples, ...

    Learning strategies to increase piglets feed intake after weaning 

    Figueroa Hamed, Jaime (Date of defense: 2012-12-18)

    En el presente trabajo se estudian diferentes estrategias de aprendizaje de la conducta alimentaria en cerdos lactantes y destetados. Los lechones podrían aprender a preferir aromas a través de su madre (Capitulo 1 y 5), ...

    Learning Styles and Reading Modes in the Development of Language Learning Autonomy through "Cybertasks" 

    Girón García, Carolina (Date of defense: 2013-10-25)

    La tesis doctoral que nos planteamos realizar se enmarca dentro de la investigación que el grupo GIAPEL (Grupo de Investigación y Aplicaciones Pedagógicas en Lenguas) ha venido realizando desde su creación en 1991. El ...

    Learning the Consensus of Multiple Correspondences between Data Structures 

    Moreno García, Carlos Francisco (Date of defense: 2016-07-12)

    En aquesta tesi presentem un marc de treball per aprendre el consens donades múltiples correspondències. S'assumeix que les diferents parts involucrades han generat aquestes correspondències per separat, i el nostre sistema ...

    Learning the Graph Edit Distance through embedding the graph matching 

    Ahmed Algabli, Shaima (Date of defense: 2020-06-17)

    Els gràfics són estructures de dades abstractes que s’utilitzen per modelar problemes reals amb dues entitats bàsiques: nodes i vores. Cada node o vèrtex representa un punt d'interès rellevant d'un problema i cada vora ...

    Learning the impact of data pre-processing in data analysis 

    Bilalli, Besim (Date of defense: 2018-06-28)

    There is a clear correlation between data availability and data analytics, and hence with the increase of data availability --- unavoidable according to Moore's law, the need for data analytics increases too. This certainly ...

    Learning to be a HERO (HEalthy & Resilient Organization): Linking organizational learning practices to healthy and resilient organizational outcomes 

    Sánchez-Cardona, Israel (Date of defense: 2017-07-10)

    Esta tesis contiene tres estudios empíricos con el propósito de entender cómo el aprendizaje es un componente esencial para el bienestar y la resiliencia en las organizaciones. Basado en el Modelo HERO, este trabajo pret ...

    Learning to extract features for 2D – 3D multimodal registration 

    Pujol Miró, Alba (Date of defense: 2020-09-18)

    The ability to capture depth information form an scene has greatly increased in the recent years. 3D sensors, traditionally high cost and low resolution sensors, are being democratized and 3D scans of indoor and outdoor ...

    Learning to identify and encode entities with deep learning models 

    Sorodoc, Ionut-Teodor (Date of defense: 2022-04-11)

    In this thesis, I tackle the ability of deep neural networks to represent entities, and I assess the extent to which this feature impacts tasks involving entities. I consider two standard architectures, LSTM and Transformer, ...

    Learning to recognize human actions: from hand-crafted to deep-learning based visual representations 

    Clapés i Sintes, Albert (Date of defense: 2019-02-04)

    Action recognition is a very challenging and important problem in computer vision. Researchers working on this field aspire to provide computers with the ability to visually perceive human actions – that is, to observe, ...

    Learning to represent handwritten shapes and words for matching and recognition 

    Almazán, Jon (Date of defense: 2014-11-21)

    La escritura es una de las formas más importantes de comunicación y durante siglos ha sido el método ma ́s fiable para preservar conocimiento. Sin embargo, a pesar del reciente desarrollo de las imprentas y dispositivos, ...

    Learning with Feed-forward Neural Networks: Three Schemes to Deal with the Bias/Variance Trade-off 

    Romero Merino, Enrique (Date of defense: 2004-11-30)

    In terms of the Bias/Variance decomposition, very flexible (i.e., complex) Supervised Machine Learning systems may lead to unbiased estimators but with high variance. A rigid model, in contrast, may lead to small variance ...

    Learning with nearest neighbour classifiers 

    Bermejo Sánchez, Sergio (Date of defense: 2000-03-29)

    Premi extraordinari ex-aequo en l'àmbit d'Electrònica i Telecomunicacions. Convocatoria 1999 - 2000

    Learning workload behaviour models from monitored time-series for resource estimation towards data center optimization 

    Buchaca Prats, David (Date of defense: 2021-01-14)

    In recent years there has been an extraordinary growth of the demand of Cloud Computing resources executed in Data Centers. Modern Data Centers are complex systems that need management. As distributed computing systems ...

    La lectura com a antropogènesi en l'obra de Marc-Alain Ouaknin: 1991-2010 

    Rodríguez i Bosch, Josep-Lluís (Date of defense: 2016-01-29)

    En aquesta tesi doctoral es fa una revisió de l'obra de Marc-Alain Ouaknin (París, 1957), rabí i filosof, influït per tres autories cabdals: Hannah Arent (acció), Paul Ricoeur (triple mimesi) i Emmanuel Lévinas (fecunditat). ...

    Lectura del "Teetet": Saviesa i prudència en el tribunal del saber 

    Ibáñez Puig, Xavier (Date of defense: 2004-05-07)

    Del <i>Teetet</i> de Plató hi ha lectures excel·lents. Però és comú a totes elles que privilegien uns fragments del text (els dedicats a la definició del saber) en detriment de tots els altres, de manera que perden, almenys ...