Deep Learning and Uncertainty Modeling in Visual Food Analysis 

    Aguilar, Eduardo (Date of defense: 2020-09-23)

    Several computer vision approaches have been proposed for tackling food analysis problems, due to the challenging problem it poses, the ease collection of food images, and its numerous applications to health and leisure. ...

    Deep Multimodal Learning for Egocentric Storytelling and Food Analysis 

    Bolaños Solà, Marc (Date of defense: 2021-04-09)

    The world of Machine Learning and Computer Vision has experienced a revolution since the last years. The appearance of Deep Learning algorithms and Convolutional Neural Networks, altogether with the increased processing ...

    Effective methods for recurrence solutions in delay differential equations 

    Gimeno i Alquézar, Joan (Date of defense: 2020-01-08)

    This thesis deals with the jet transport for numerical integrators and the effective invariant object computation of delay differential equations. Firstly we study how automatic differentiation (AD) affects when ...

    Efficient and convergent natural gradient based optimization algorithms for machine learning 

    Sánchez López, Borja (Date of defense: 2022-11-22)

    [eng] Many times machine learning is casted as an optimization problem. This is the case when an objective function assesses the success of an agent in a certain task and hence, learning is accomplished by optimizing that ...

    Evolutionary Bags of Space-Time Features for Human Analysis 

    Ponce López, Víctor (Date of defense: 2016-06-02)

    The representation (or feature) learning has been an emerging concept in the last years, since it collects a set of techniques that are present in any theoretical or practical methodology referring to artificial intelligence. ...

    Finite groups acting on smooth and symplectic 4-manifolds 

    Sáez Calvo, Carles (Date of defense: 2019-07-22)

    En esta tesis se estudian problemas relacionados con acciones de grupos finitos en 4-variedades diferenciables y simplécticas. Se prueba que toda 4-variedad diferenciable cerrada X admite una constante C>0 tal que cualquier ...

    Function and Operator Theory on Large Bergman spaces 

    Arroussi, Hicham (Date of defense: 2016-05-06)

    The theory of Bergman spaces has been a central subject of study in complex analysis during the past decades. The book [7] by S. Bergman contains the first systematic treat-ment of the Hilbert space of square integrable ...

    Gorenstein colength of local Artin k-algebras 

    Homs Pons, Roser (Date of defense: 2019-07-24)

    En esta tesis abordamos el problema de la aproximación de anillos locales por anillos de Gorenstein en el caso cero-dimensional. Nos centramos en el estudio y el cálculo efectivo de la colongitud de Gorenstein, una noción ...

    Gröbner's problem and the geometry of GT-varieties 

    Colarte Gómez, Liena (Date of defense: 2021-07-20)

    Within the framework of algebraic geometry and commutative algebra, this thesis makes advances in (1) the Gröbner's longstanding problem of determining whether a monomial projection of the Veronese variety Vn,d is an aCM ...

    Hankel operators on vector-valued Bergman spaces 

    Oliver Vendrell, Roc (Date of defense: 2017-09-14)

    The main goal of this work is to study vector-valued Bergman spaces and to obtain the weak factorization of these spaces. In order to do that we need to study small Hankel operators with operator-valued holomorphic symbols. ...

    Higher regularity of free boundaries in obstacle problems 

    Kukuljan, Teo (Date of defense: 2022-10-07)

    In the thesis we consider higher regularity of the free boundaries in different variations of the obstacle problem, that is, when the Laplace operator b. is replaced with another elliptic or parabolic operator. In the ...

    Hitting probabilities for g-Gaussian processes 

    Hinojosa Calleja, Adrián (Date of defense: 2022-04-07)

    We develop criteria for hitting probabilities of Gaussian random fields with associated canonical metric given by a class of gauge functions. This yields upper and lower bounds in terms of general notions of Hausdorff ...

    Improving Performance and Interpretability in Recognizing Facial Action Units with Deep Neural Networks 

    Corneanu, Cipiran Adrian (Date of defense: 2019-12-13)

    Facial expressions are vital ways of communication between humans in social contexts. They are used as conversational markers and they convey information about affective and cognitive state. Many applications would benefit ...

    Integración de técnicas de personalización basadas en el comportamiento colaborativo del ser humano con interfaces de usuario inteligentes 

    Contreras Aguilar, David (Date of defense: 2017-07-21)

    Esta tesis está enfocada en la problemática asociada a la personalización de información para usuarios que interactúan con grandes volúmenes de información. En concreto, la tesis se centra en el estudio de los sistemas de ...

    Invariant manifolds and transport in a Sun-perturbed Earth-Moon system 

    Nicolás Ávila, Begoña (Date of defense: 2022-04-22)

    This dissertation is devoted to the analysis of the motion of small bodies, like asteroids, in the neighbourhood of the Earth-Moon system from a celestial mechanics approach. This is an extensive area of research where ...

    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, ...

    Lifestyle Understanding through the Analysis of Egocentric Photo-streams 

    Talavera Martínez, Estefanía (Date of defense: 2020-02-14)

    Describing people’s lives has become a hot topic in several disciplines. Lifelogging appeared in the 1960s as the process of recording and tracking personal activity data generated by the daily behaviour of a person. The ...

    Modelling Uncertainty in Black-box Classification Systems 

    Mena Roldán, José (Date of defense: 2020-12-15)

    Currently, thanks to the Big Data boom, the excellent results obtained by deep learning models and the strong digital transformation experienced over the last years, many companies have decided to incorporate machine ...

    New results on modular forms and Fermat-type equations 

    Soto Ballesteros, Eduardo (Date of defense: 2019-11-11)

    Aquesta tesi té dos objectius. El primer és contribuir en la teoria de congruències entre formes modulars via representacions de Galois. El segon és resoldre nous problemes diofantins de tipus Fermat. En quant a representacions ...

    On Logics and Semantics for Interpretability 

    Mikec, Luka (Date of defense: 2021-04-30)

    In the central part of this thesis we study for different interpretability logics the following aspects: completeness for modal semantics, decidability and algorithmic complexity. In particular, we will study two basic ...